SAML
Society-Aware Machine Learning (SAML)
SAML is a European Research Council (ERC) Starting Grant project focused on developing machine learning systems that are not only accurate and efficient but also fair, transparent, and socially responsible. By incorporating the perspectives of multiple stakeholders throughout the AI development process, SAML aims to create trustworthy and human-centered AI technologies.
This work is funded by the European Union through the ERC Starting Grant programme (Grant Agreement No. 101040177).
ERC Summary & Objectives
Objective 1: Developing a Society-Aware Machine Learning Framework
SAML establishes the methodological foundations for society-aware machine learning, where algorithms are designed and evaluated by explicitly accounting for the utilities, preferences, and welfare of all relevant stakeholders. This required addressing several fundamental technical challenges, including estimating the causal consequences of decisions and actions, comparing competing stakeholder objectives, and extending fairness assessment beyond traditional prediction-based metrics.
We developed new methods for causal inference that estimate the downstream consequences of decisions under realistic conditions, including hidden confounding and temporal dynamics (DeCaFlow, A Practical Approach to Causal Inference over Time).
We further introduced methods for comparing and jointly optimizing diverse objectives, integrating preferences and allowing practitioners to systematically explore Pareto-optimal trade-offs (COPA, Hellinger Multimodal Variational Autoencoders, Hyper-Transforming Latent Diffusion Models).
Building on these technical foundations, we established new frameworks for fairness assessment that move beyond binary decision outcomes by considering treatment decisions, their downstream consequences, long-term societal effects, and the welfare of multiple stakeholders (A Causal Framework to Measure and Mitigate Non-binary Treatment Discrimination, Fairness Beyond Binary Decisions, Designing Long-term Group Fair Policies in Dynamical Systems, Long-term Fairness with Selective Labels, First-See-Then-Design).
Objective 2: Achieving Consensual Machine Learning
Building on methodological advances (summarized under Objective 1), SAML develops machine learning methods that seek solutions benefiting all involved stakeholders.
We introduced decision-making frameworks that explicitly balance the utilities of system deployers, affected individuals, and society, enabling transparent exploration of performance–fairness trade-offs and the design of policies that remain fair over time (First-See-Then-Design, Designing Long-term Group Fair Policies in Dynamical Systems, Long-term Fairness with Selective Labels).
Beyond institutional decision-making, SAML empowers individuals affected by automated decisions. We develop a framework allowing individuals to overcome negative automated decisions through personalized algorithmic recourse that accounts for their preferences and constraints (From Universal to Individualized Actionability).
Finally, SAML improves the transparency and interpretability of machine learning by making trade-offs between competing objectives explicit and by developing inherently interpretable models that better expose the reasoning behind automated decisions (COPA, First-See-Then-Design, Towards Reasonable Concept Bottleneck Models).
Objective:3 Addressing Ethical Challenges in Machine Learning
The methodological advances developed throughout SAML translate into practical solutions for addressing ethical challenges arising from the deployment of machine learning in society.
We developed methods to identify and mitigate unfairness in high-stakes applications such as lending by uncovering previously overlooked forms of discrimination, extending fairness assessment beyond conventional metrics, and evaluating fairness in modern AI systems such as large language models (A Causal Framework to Measure and Mitigate Non-binary Treatment Discrimination, Fairness Beyond Binary Decisions, Accept or Deny? Evaluating LLM Fairness and Performance in Loan Approval, On the Misalignment Between Legal Notions and Statistical Metrics of Intersectional Fairness).
In parallel, the project increases individuals’ ability to respond to automated decisions through personalized recourse while improving the transparency and accountability of AI systems through interpretable models and explicit analysis of trade-offs between competing objectives (From Universal to Individualized Actionability, Towards Reasonable Concept Bottleneck Models).
SAML Publications
2026
Gupta, Kavya; Kalampalikis, Nektarios; Heitz, Christoph; Valera, Isabel
First-See-Then-Design: A Multi-Stakeholder View for Optimal Performance-Fairness Trade-Offs Proceedings Article
In: Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency, pp. 218–248, ACM, 2026.
Abstract | Links | BibTeX | Tags: isabel, kavya, nektarios, saml
@inproceedings{Gupta_2026,
title = {First-See-Then-Design: A Multi-Stakeholder View for Optimal Performance-Fairness Trade-Offs},
author = {Kavya Gupta and Nektarios Kalampalikis and Christoph Heitz and Isabel Valera},
url = {http://dx.doi.org/10.1145/3805689.3806541},
doi = {10.1145/3805689.3806541},
year = {2026},
date = {2026-06-01},
urldate = {2026-06-01},
booktitle = {Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency},
pages = {218–248},
publisher = {ACM},
series = {FAccT ’26},
abstract = {Fairness in algorithmic decision-making is often defined in the predictive space, where predictive performance - used as a proxy for decision-maker (DM) utility - is traded off against prediction-based fairness notions, such as demographic parity or equality of opportunity. This perspective, however, ignores how predictions translate into decisions and ultimately into utilities and welfare for both DM and decision subjects (DS), as well as their allocation across social-salient groups.
In this paper, we propose a multi-stakeholder framework for fair algorithmic decision-making grounded in welfare economics and distributive justice, explicitly modeling the utilities of both the DM and DS, and defining fairness via a social planner's utility that captures inequalities in DS utilities across groups under different justice-based fairness notions (e.g., Egalitarian, Rawlsian). We formulate fair decision-making as a post-hoc multi-objective optimization problem, characterizing the achievable performance-fairness trade-offs in the two-dimensional utility space of DM utility and the social planner's utility, under different decision policy classes (deterministic vs. stochastic, shared vs. group-specific). Using the proposed framework, we then identify conditions (in terms of the stakeholders' utilities) under which stochastic policies are more optimal than deterministic ones, and empirically demonstrate that simple stochastic policies can yield superior performance-fairness trade-offs by leveraging outcome uncertainty. Overall, we advocate a shift from prediction-centric fairness to a transparent, justice-based, multi-stakeholder approach that supports the collaborative design of decision-making policies.},
keywords = {isabel, kavya, nektarios, saml},
pubstate = {published},
tppubtype = {inproceedings}
}
Fairness in algorithmic decision-making is often defined in the predictive space, where predictive performance - used as a proxy for decision-maker (DM) utility - is traded off against prediction-based fairness notions, such as demographic parity or equality of opportunity. This perspective, however, ignores how predictions translate into decisions and ultimately into utilities and welfare for both DM and decision subjects (DS), as well as their allocation across social-salient groups.
In this paper, we propose a multi-stakeholder framework for fair algorithmic decision-making grounded in welfare economics and distributive justice, explicitly modeling the utilities of both the DM and DS, and defining fairness via a social planner's utility that captures inequalities in DS utilities across groups under different justice-based fairness notions (e.g., Egalitarian, Rawlsian). We formulate fair decision-making as a post-hoc multi-objective optimization problem, characterizing the achievable performance-fairness trade-offs in the two-dimensional utility space of DM utility and the social planner's utility, under different decision policy classes (deterministic vs. stochastic, shared vs. group-specific). Using the proposed framework, we then identify conditions (in terms of the stakeholders' utilities) under which stochastic policies are more optimal than deterministic ones, and empirically demonstrate that simple stochastic policies can yield superior performance-fairness trade-offs by leveraging outcome uncertainty. Overall, we advocate a shift from prediction-centric fairness to a transparent, justice-based, multi-stakeholder approach that supports the collaborative design of decision-making policies.
In this paper, we propose a multi-stakeholder framework for fair algorithmic decision-making grounded in welfare economics and distributive justice, explicitly modeling the utilities of both the DM and DS, and defining fairness via a social planner's utility that captures inequalities in DS utilities across groups under different justice-based fairness notions (e.g., Egalitarian, Rawlsian). We formulate fair decision-making as a post-hoc multi-objective optimization problem, characterizing the achievable performance-fairness trade-offs in the two-dimensional utility space of DM utility and the social planner's utility, under different decision policy classes (deterministic vs. stochastic, shared vs. group-specific). Using the proposed framework, we then identify conditions (in terms of the stakeholders' utilities) under which stochastic policies are more optimal than deterministic ones, and empirically demonstrate that simple stochastic policies can yield superior performance-fairness trade-offs by leveraging outcome uncertainty. Overall, we advocate a shift from prediction-centric fairness to a transparent, justice-based, multi-stakeholder approach that supports the collaborative design of decision-making policies.
Majumdar, Ayan; Kanubala, Deborah Dormah; Gupta, Kavya; Valera, Isabel
A Causal Framework to Measure and Mitigate Non-binary Treatment Discrimination Journal Article
In: CoRR, vol. abs/2503.22454, 2026.
Abstract | Links | BibTeX | Tags: ayanm, deborah, isabel, kavya, saml
@article{DBLP:journals/corr/abs-2503-22454,
title = {A Causal Framework to Measure and Mitigate Non-binary Treatment Discrimination},
author = {Ayan Majumdar and Deborah Dormah Kanubala and Kavya Gupta and Isabel Valera},
url = {https://doi.org/10.48550/arXiv.2503.22454},
doi = {10.48550/ARXIV.2503.22454},
year = {2026},
date = {2026-03-19},
urldate = {2026-03-19},
journal = {CoRR},
volume = {abs/2503.22454},
abstract = {Fairness studies of algorithmic decision-making systems often simplify complex decision processes, such as bail or lending decisions, into binary classification tasks (e.g., approve or not approve). However, these approaches overlook that such decisions are not inherently binary; they also involve non-binary treatment decisions (e.g., loan or bail terms) that can influence the downstream outcomes (e.g., loan repayment or reoffending). We argue that treatment decisions are integral to the decision-making process and, therefore, should be central to fairness analyses. Consequently, we propose a causal framework that extends and complements existing fairness notions by explicitly distinguishing between decision-subjects’ covariates and the treatment decisions. Our framework leverages path-specific counterfactual reasoning to: (i) measure treatment disparity and its downstream effects in historical data; and (ii) mitigate the impact of past unfair treatment decisions when automating decision-making. We use our framework to empirically analyze four widely used loan approval datasets to reveal potential disparity in non-binary treatment decisions and their discriminatory impact on outcomes, highlighting the need to incorporate treatment decisions in fairness assessments. Finally, by intervening in treatment decisions, we show that our framework effectively mitigates treatment discrimination from historical loan approval data to ensure fair risk score estimation and (non-binary) decision-making processes that benefit all stakeholders.},
keywords = {ayanm, deborah, isabel, kavya, saml},
pubstate = {published},
tppubtype = {article}
}
Fairness studies of algorithmic decision-making systems often simplify complex decision processes, such as bail or lending decisions, into binary classification tasks (e.g., approve or not approve). However, these approaches overlook that such decisions are not inherently binary; they also involve non-binary treatment decisions (e.g., loan or bail terms) that can influence the downstream outcomes (e.g., loan repayment or reoffending). We argue that treatment decisions are integral to the decision-making process and, therefore, should be central to fairness analyses. Consequently, we propose a causal framework that extends and complements existing fairness notions by explicitly distinguishing between decision-subjects’ covariates and the treatment decisions. Our framework leverages path-specific counterfactual reasoning to: (i) measure treatment disparity and its downstream effects in historical data; and (ii) mitigate the impact of past unfair treatment decisions when automating decision-making. We use our framework to empirically analyze four widely used loan approval datasets to reveal potential disparity in non-binary treatment decisions and their discriminatory impact on outcomes, highlighting the need to incorporate treatment decisions in fairness assessments. Finally, by intervening in treatment decisions, we show that our framework effectively mitigates treatment discrimination from historical loan approval data to ensure fair risk score estimation and (non-binary) decision-making processes that benefit all stakeholders.
Vo, Huyen; Martı́nez-Garcı́a, Marı́a; Valera, Isabel
Holder++: Improving the Quality-Coherence Trade-off in Multimodal VAEs Proceedings Article
In: 2026.
Abstract | Links | BibTeX | Tags: huyen, isabel, maria, saml
@inproceedings{nokey,
title = {Holder++: Improving the Quality-Coherence Trade-off in Multimodal VAEs},
author = {Huyen Vo and Marı́a Martı́nez-Garcı́a and Isabel Valera},
url = {https://vothuckhanhhuyen.github.io/assets/pdf/Holder_ICML2026.pdf},
year = {2026},
date = {2026-03-11},
urldate = {2026-03-11},
abstract = {Existing approaches for multimodal variational autoencoders (VAEs) face a trade-off between generative quality and coherence—i.e., they struggle to generate realistic and diverse samples that, at the same time, are semantically consistent across modalities. A recent work shows that using a simple approximation to Hölder pooling as an aggregation method improves coherence over the SOTA MMVAE+, despite assuming a single shared representation across all modalities. Yet, it slightly compromises sample diversity. Inspired by this insight, we propose Hölder++, a novel multimodal VAE that improves the generative quality-coherence trade-off through: (i) the first implementation of Hölder pooling without any approximation for multimodal VAEs; (ii) an extended architecture that models distinct shared and private (i.e., modality-specific) representations (Hölder+); and (iii) hierarchical inference that further enhances the disentanglement between the shared and private representations (Hölder++). Our experiments corroborate that Hölder++ consistently improves the generative quality-coherence trade-off, yields more structured latent spaces, and learns shared representations that are informative for downstream tasks.},
keywords = {huyen, isabel, maria, saml},
pubstate = {published},
tppubtype = {inproceedings}
}
Existing approaches for multimodal variational autoencoders (VAEs) face a trade-off between generative quality and coherence—i.e., they struggle to generate realistic and diverse samples that, at the same time, are semantically consistent across modalities. A recent work shows that using a simple approximation to Hölder pooling as an aggregation method improves coherence over the SOTA MMVAE+, despite assuming a single shared representation across all modalities. Yet, it slightly compromises sample diversity. Inspired by this insight, we propose Hölder++, a novel multimodal VAE that improves the generative quality-coherence trade-off through: (i) the first implementation of Hölder pooling without any approximation for multimodal VAEs; (ii) an extended architecture that models distinct shared and private (i.e., modality-specific) representations (Hölder+); and (iii) hierarchical inference that further enhances the disentanglement between the shared and private representations (Hölder++). Our experiments corroborate that Hölder++ consistently improves the generative quality-coherence trade-off, yields more structured latent spaces, and learns shared representations that are informative for downstream tasks.
Uth, Richard; Niemitz, Nelli; Valera, Isabel; Langer, Markus
Personalizing explanations in AI-based decisions: The effects of personalization and (Mis)aligning with individual preferences Journal Article
In: Computers in Human Behavior, 2026.
Abstract | Links | BibTeX | Tags: isabel
@article{Uth2025PersonalizingEI,
title = {Personalizing explanations in AI-based decisions: The effects of personalization and (Mis)aligning with individual preferences},
author = {Richard Uth and Nelli Niemitz and Isabel Valera and Markus Langer},
url = {https://api.semanticscholar.org/CorpusID:283171660},
year = {2026},
date = {2026-02-03},
urldate = {2025-01-01},
journal = {Computers in Human Behavior},
abstract = {The increasing reliance on AI-based decision-making in high-stakes contexts underscores the need for transparency and justice. Here, negative outcomes drive individuals affected by AI-based decisions to seek actionable explanations that enable them to realize what they can do to achieve a better future outcome. However, actionability is subjective, varying across individuals and contexts. Personalization of explanations has been proposed to address this variability, but insights on personalized explanation processes, their potential, and challenges are scarce. This paper investigates the impact of personalization and (mis)alignment with individual needs and preferences in explanations for AI-based decisions through an experimental online study simulating denied loan applications. In a within-participants design (N=255), participants ranked the actionability of decision-relevant features and experienced five explanation conditions: personalized directive explanations based on the most, second most, or least actionable feature (as ranked by participants); a non-personalized directive explanation highlighting a random feature; and no explanation. In line with justice theory, our results show that any explanation was better than none, and that personalized explanations led to more favorable reactions than non-personalized explanations, enhancing perceptions of justice and attractiveness of the bank. Closer alignment with preferences had only small positive effects, mainly for attractiveness. These findings highlight that even simple ranking-based approaches can make explanations more effective and accessible without requiring technical expertise while cautioning against offering superficial control. This study provides insights into the effects of ranking-based personalization, informing the design of explainability tailored to diverse user needs and addressing ethical and practical considerations in personalization.},
keywords = {isabel},
pubstate = {published},
tppubtype = {article}
}
The increasing reliance on AI-based decision-making in high-stakes contexts underscores the need for transparency and justice. Here, negative outcomes drive individuals affected by AI-based decisions to seek actionable explanations that enable them to realize what they can do to achieve a better future outcome. However, actionability is subjective, varying across individuals and contexts. Personalization of explanations has been proposed to address this variability, but insights on personalized explanation processes, their potential, and challenges are scarce. This paper investigates the impact of personalization and (mis)alignment with individual needs and preferences in explanations for AI-based decisions through an experimental online study simulating denied loan applications. In a within-participants design (N=255), participants ranked the actionability of decision-relevant features and experienced five explanation conditions: personalized directive explanations based on the most, second most, or least actionable feature (as ranked by participants); a non-personalized directive explanation highlighting a random feature; and no explanation. In line with justice theory, our results show that any explanation was better than none, and that personalized explanations led to more favorable reactions than non-personalized explanations, enhancing perceptions of justice and attractiveness of the bank. Closer alignment with preferences had only small positive effects, mainly for attractiveness. These findings highlight that even simple ranking-based approaches can make explanations more effective and accessible without requiring technical expertise while cautioning against offering superficial control. This study provides insights into the effects of ranking-based personalization, informing the design of explainability tailored to diverse user needs and addressing ethical and practical considerations in personalization.
Müller, Nicola J.; Oster, Moritz; Valera, Isabel; Hoffmann, Jörg; Gros, Timo P.
Per-Domain Generalizing Policies: On Learning Efficient and Robust Q-Value Functions (Extended Version with Technical Appendix) Journal Article
In: CoRR, vol. abs/2603.17544, 2026.
Abstract | Links | BibTeX | Tags: isabel
@article{DBLP:journals/corr/abs-2603-17544,
title = {Per-Domain Generalizing Policies: On Learning Efficient and Robust Q-Value Functions (Extended Version with Technical Appendix)},
author = {Nicola J. Müller and Moritz Oster and Isabel Valera and Jörg Hoffmann and Timo P. Gros},
url = {https://doi.org/10.48550/arXiv.2603.17544},
doi = {10.48550/ARXIV.2603.17544},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
journal = {CoRR},
volume = {abs/2603.17544},
abstract = {Learning per-domain generalizing policies is a key challenge in learning for planning. Standard approaches learn state-value functions represented as graph neural networks using supervised learning on optimal plans generated by a teacher planner. In this work, we advocate for learning Q-value functions instead. Such policies are drastically cheaper to evaluate for a given state, as they need to process only the current state rather than every successor. Surprisingly, vanilla supervised learning of Q-values performs poorly as it does not learn to distinguish between the actions taken and those not taken by the teacher. We address this by using regularization terms that enforce this distinction, resulting in Q-value policies that consistently outperform state-value policies across a range of 10 domains and are competitive with the planner LAMA-first.},
keywords = {isabel},
pubstate = {published},
tppubtype = {article}
}
Learning per-domain generalizing policies is a key challenge in learning for planning. Standard approaches learn state-value functions represented as graph neural networks using supervised learning on optimal plans generated by a teacher planner. In this work, we advocate for learning Q-value functions instead. Such policies are drastically cheaper to evaluate for a given state, as they need to process only the current state rather than every successor. Surprisingly, vanilla supervised learning of Q-values performs poorly as it does not learn to distinguish between the actions taken and those not taken by the teacher. We address this by using regularization terms that enforce this distinction, resulting in Q-value policies that consistently outperform state-value policies across a range of 10 domains and are competitive with the planner LAMA-first.
Vo, Huyen Thuc Khanh; Valera, Isabel
Hellinger Multimodal Variational Autoencoders Proceedings Article Spotlight
In: The 29th International Conference on Artificial Intelligence and Statistics, 2026.
Abstract | Links | BibTeX | Tags: huyen, isabel, saml, spotlight
@inproceedings{<LineBreak>vo2026hellinger,
title = {Hellinger Multimodal Variational Autoencoders},
author = {Huyen Thuc Khanh Vo and Isabel Valera},
url = {https://openreview.net/forum?id=mxHyYltMUa},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
booktitle = {The 29th International Conference on Artificial Intelligence and Statistics},
abstract = {Multimodal variational autoencoders (VAEs) are widely used for weakly supervised generative learning with multiple modalities. Predominant methods aggregate unimodal inference distributions using either a product of experts (PoE), a mixture of experts (MoE), or their combinations to approximate the joint posterior. In this work, we revisit multimodal inference through the lens of probabilistic opinion pooling, an optimization-based approach. We start from Hölder pooling with α=0.5, which corresponds to the unique symmetric member of the α-divergence family, and derive a moment-matching approximation, termed Hellinger. We then leverage such an approximation to propose HELVAE, a multimodal VAE that avoids sub-sampling, yielding an efficient yet effective model that: (i) learns more expressive latent representations as additional modalities are observed; and (ii) empirically achieves better trade-offs between generative coherence and quality, outperforming state-of-the-art multimodal VAE models.},
keywords = {huyen, isabel, saml, spotlight},
pubstate = {published},
tppubtype = {inproceedings}
}
Multimodal variational autoencoders (VAEs) are widely used for weakly supervised generative learning with multiple modalities. Predominant methods aggregate unimodal inference distributions using either a product of experts (PoE), a mixture of experts (MoE), or their combinations to approximate the joint posterior. In this work, we revisit multimodal inference through the lens of probabilistic opinion pooling, an optimization-based approach. We start from Hölder pooling with α=0.5, which corresponds to the unique symmetric member of the α-divergence family, and derive a moment-matching approximation, termed Hellinger. We then leverage such an approximation to propose HELVAE, a multimodal VAE that avoids sub-sampling, yielding an efficient yet effective model that: (i) learns more expressive latent representations as additional modalities are observed; and (ii) empirically achieves better trade-offs between generative coherence and quality, outperforming state-of-the-art multimodal VAE models.
Valdrighi, Giovani; Valera, Isabel; Raimundo, Marcos Medeiros
Long-term Fairness with Selective Labels Proceedings Article
In: 2026.
Abstract | Links | BibTeX | Tags: isabel, saml
@inproceedings{valdrighi2026longtermfairnessselectivelabels,
title = {Long-term Fairness with Selective Labels},
author = {Giovani Valdrighi and Isabel Valera and Marcos Medeiros Raimundo},
url = {https://arxiv.org/abs/2605.22291},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
abstract = {Long-term fairness algorithms aim to satisfy fairness beyond static and short-term notions by accounting for the dynamics between decision-making policies and population behavior. Most previous approaches evaluate performance and fairness measures from observable features and a label, which is assumed to be fully observed. However, in scenarios such as hiring or lending, the labels (e.g., ability to repay the loan) are selective labels as they are only revealed based on positive decisions (e.g., when a loan is granted). In this paper, we study long-term fairness in the selective labels setting and analytically show that naive solutions do not guarantee fairness. To address this gap, we then introduce a novel framework that leverages both the observed data and a label predictor model to estimate the true fairness measure value by decomposing it into the observed fairness and bias from label predictions. This allows us to derive sufficient conditions to satisfy true fairness from observable quantities by using the confidence in the predictor model. Finally, we rely on our theoretical results to propose a novel reinforcement learning algorithm for effective long-term fair decision-making with selective labels. In semisynthetic environments, the proposed algorithm reached comparable fairness and performance to an agent with oracle access to the true labels.},
keywords = {isabel, saml},
pubstate = {published},
tppubtype = {inproceedings}
}
Long-term fairness algorithms aim to satisfy fairness beyond static and short-term notions by accounting for the dynamics between decision-making policies and population behavior. Most previous approaches evaluate performance and fairness measures from observable features and a label, which is assumed to be fully observed. However, in scenarios such as hiring or lending, the labels (e.g., ability to repay the loan) are selective labels as they are only revealed based on positive decisions (e.g., when a loan is granted). In this paper, we study long-term fairness in the selective labels setting and analytically show that naive solutions do not guarantee fairness. To address this gap, we then introduce a novel framework that leverages both the observed data and a label predictor model to estimate the true fairness measure value by decomposing it into the observed fairness and bias from label predictions. This allows us to derive sufficient conditions to satisfy true fairness from observable quantities by using the confidence in the predictor model. Finally, we rely on our theoretical results to propose a novel reinforcement learning algorithm for effective long-term fair decision-making with selective labels. In semisynthetic environments, the proposed algorithm reached comparable fairness and performance to an agent with oracle access to the true labels.
Budde, Lena Marie; Majumdar, Ayan; Uth, Richard; Langer, Markus; Valera, Isabel
From Universal to Individualized Actionability: Revisiting Personalization in Algorithmic Recourse Proceedings Article
In: 2026.
Abstract | Links | BibTeX | Tags: isabel, saml
@inproceedings{budde2026universalindividualizedactionabilityrevisiting,
title = {From Universal to Individualized Actionability: Revisiting Personalization in Algorithmic Recourse},
author = {Lena Marie Budde and Ayan Majumdar and Richard Uth and Markus Langer and Isabel Valera},
url = {https://arxiv.org/abs/2604.08030},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
abstract = {Algorithmic recourse aims to provide actionable recommendations that enable individuals to change unfavorable model outcomes, and prior work has extensively studied properties such as efficiency, robustness, and fairness. However, the role of personalization in recourse remains largely implicit and underexplored. While existing approaches incorporate elements of personalization through user interactions, they typically lack an explicit definition of personalization and do not systematically analyze its downstream effects on other recourse desiderata.
In this paper, we formalize personalization as individual actionability, characterized along two dimensions: hard constraints that specify which features are individually actionable, and soft, individualized constraints that capture preferences over action values and costs. We operationalize these dimensions within the causal algorithmic recourse framework, adopting a pre-hoc user-prompting approach in which individuals express preferences via rankings or scores prior to the generation of any recourse recommendation. Through extensive empirical evaluation, we investigate how personalization interacts with key recourse desiderata, including validity, cost, and plausibility. Our results highlight important trade-offs: individual actionability constraints, particularly hard ones, can substantially degrade the plausibility and validity of recourse recommendations across amortized and non-amortized approaches. Notably, we also find that incorporating individual actionability can reveal disparities in the cost and plausibility of recourse actions across socio-demographic groups. These findings underscore the need for principled definitions, careful operationalization, and rigorous evaluation of personalization in algorithmic recourse.},
keywords = {isabel, saml},
pubstate = {published},
tppubtype = {inproceedings}
}
Algorithmic recourse aims to provide actionable recommendations that enable individuals to change unfavorable model outcomes, and prior work has extensively studied properties such as efficiency, robustness, and fairness. However, the role of personalization in recourse remains largely implicit and underexplored. While existing approaches incorporate elements of personalization through user interactions, they typically lack an explicit definition of personalization and do not systematically analyze its downstream effects on other recourse desiderata.
In this paper, we formalize personalization as individual actionability, characterized along two dimensions: hard constraints that specify which features are individually actionable, and soft, individualized constraints that capture preferences over action values and costs. We operationalize these dimensions within the causal algorithmic recourse framework, adopting a pre-hoc user-prompting approach in which individuals express preferences via rankings or scores prior to the generation of any recourse recommendation. Through extensive empirical evaluation, we investigate how personalization interacts with key recourse desiderata, including validity, cost, and plausibility. Our results highlight important trade-offs: individual actionability constraints, particularly hard ones, can substantially degrade the plausibility and validity of recourse recommendations across amortized and non-amortized approaches. Notably, we also find that incorporating individual actionability can reveal disparities in the cost and plausibility of recourse actions across socio-demographic groups. These findings underscore the need for principled definitions, careful operationalization, and rigorous evaluation of personalization in algorithmic recourse.
In this paper, we formalize personalization as individual actionability, characterized along two dimensions: hard constraints that specify which features are individually actionable, and soft, individualized constraints that capture preferences over action values and costs. We operationalize these dimensions within the causal algorithmic recourse framework, adopting a pre-hoc user-prompting approach in which individuals express preferences via rankings or scores prior to the generation of any recourse recommendation. Through extensive empirical evaluation, we investigate how personalization interacts with key recourse desiderata, including validity, cost, and plausibility. Our results highlight important trade-offs: individual actionability constraints, particularly hard ones, can substantially degrade the plausibility and validity of recourse recommendations across amortized and non-amortized approaches. Notably, we also find that incorporating individual actionability can reveal disparities in the cost and plausibility of recourse actions across socio-demographic groups. These findings underscore the need for principled definitions, careful operationalization, and rigorous evaluation of personalization in algorithmic recourse.
Martínez-García, María; Alvarez, Ricardo Vazquez; Lancho, Alejandro; Olmos, Pablo M.; Valera, Isabel
A Probabilistic Hard Concept Bottleneck for Steerable Generative Models Proceedings Article
In: The Fourteenth International Conference on Learning Representations, 2026.
Abstract | Links | BibTeX | Tags: isabel, maria, pablo, saml
@inproceedings{<LineBreak>martinez-garcia2026a,
title = {A Probabilistic Hard Concept Bottleneck for Steerable Generative Models},
author = {María Martínez-García and Ricardo Vazquez Alvarez and Alejandro Lancho and Pablo M. Olmos and Isabel Valera},
url = {https://openreview.net/forum?id=Kcb6WufAco},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
booktitle = {The Fourteenth International Conference on Learning Representations},
abstract = {Concept Bottleneck Generative Models (CBGMs) incorporate a human-interpretable concept bottleneck layer, which makes them interpretable and steerable. However, designing such a layer for generative models poses the same challenges as for concept bottleneck models in a supervised context, if not greater ones. Deterministic mappings from the model inner representations to soft concepts in existing CBGMs: (i) limit steerable generation to modifying concepts in existing inputs; and, more importantly, (ii) are susceptible to concept leakage, which hinders their steerability. To address these limitations, we first introduce the Variational Hard Concept Bottleneck (VHCB) layer. The VHCB maps probabilistic estimates of binary latent variables to hard concepts, which have been shown to mitigate leakage. Remarkably, its probabilistic formulation enables direct generation from a specified set of concepts. Second, we propose a systematic evaluation framework for assessing the steerability of CBGMs across various tasks (e.g., activating and deactivating concepts). Our framework which allows us to empirically demonstrate that the VHCB layer consistently improves steerability.},
keywords = {isabel, maria, pablo, saml},
pubstate = {published},
tppubtype = {inproceedings}
}
Concept Bottleneck Generative Models (CBGMs) incorporate a human-interpretable concept bottleneck layer, which makes them interpretable and steerable. However, designing such a layer for generative models poses the same challenges as for concept bottleneck models in a supervised context, if not greater ones. Deterministic mappings from the model inner representations to soft concepts in existing CBGMs: (i) limit steerable generation to modifying concepts in existing inputs; and, more importantly, (ii) are susceptible to concept leakage, which hinders their steerability. To address these limitations, we first introduce the Variational Hard Concept Bottleneck (VHCB) layer. The VHCB maps probabilistic estimates of binary latent variables to hard concepts, which have been shown to mitigate leakage. Remarkably, its probabilistic formulation enables direct generation from a specified set of concepts. Second, we propose a systematic evaluation framework for assessing the steerability of CBGMs across various tasks (e.g., activating and deactivating concepts). Our framework which allows us to empirically demonstrate that the VHCB layer consistently improves steerability.
Wang, Yifan; Jobanputra, Mayank; Lee, Ji-Ung; Oh, Soyoung; Valera, Isabel; Demberg, Vera
Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection? Proceedings Article
In: The Fourteenth International Conference on Learning Representations, 2026.
Abstract | Links | BibTeX | Tags: isabel, yifan
@inproceedings{<LineBreak>wang2026bridging,
title = {Bridging Fairness and Explainability: Can Input-Based Explanations Promote Fairness in Hate Speech Detection?},
author = {Yifan Wang and Mayank Jobanputra and Ji-Ung Lee and Soyoung Oh and Isabel Valera and Vera Demberg},
url = {https://openreview.net/forum?id=fPMu3Afv3s},
year = {2026},
date = {2026-01-01},
urldate = {2026-01-01},
booktitle = {The Fourteenth International Conference on Learning Representations},
abstract = {Natural language processing (NLP) models often replicate or amplify social bias from training data, raising concerns about fairness. At the same time, their black-box nature makes it difficult for users to recognize biased predictions and for developers to effectively mitigate them. While some studies suggest that input-based explanations can help detect and mitigate bias, others question their reliability in ensuring fairness. Existing research on explainability in fair NLP has been predominantly qualitative, with limited large-scale quantitative analysis. In this work, we conduct the first systematic study of the relationship between explainability and fairness in hate speech detection, focusing on both encoder- and decoder-only models. We examine three key dimensions: (1) identifying biased predictions, (2) selecting fair models, and (3) mitigating bias during model training. Our findings show that input-based explanations can effectively detect biased predictions and serve as useful supervision for reducing bias during training, but they are unreliable for selecting fair models among this http URL http://candidates.our/ code is available at this URL https://github.com/Ewanwong/fairness_x_explainability},
keywords = {isabel, yifan},
pubstate = {published},
tppubtype = {inproceedings}
}
Natural language processing (NLP) models often replicate or amplify social bias from training data, raising concerns about fairness. At the same time, their black-box nature makes it difficult for users to recognize biased predictions and for developers to effectively mitigate them. While some studies suggest that input-based explanations can help detect and mitigate bias, others question their reliability in ensuring fairness. Existing research on explainability in fair NLP has been predominantly qualitative, with limited large-scale quantitative analysis. In this work, we conduct the first systematic study of the relationship between explainability and fairness in hate speech detection, focusing on both encoder- and decoder-only models. We examine three key dimensions: (1) identifying biased predictions, (2) selecting fair models, and (3) mitigating bias during model training. Our findings show that input-based explanations can effectively detect biased predictions and serve as useful supervision for reducing bias during training, but they are unreliable for selecting fair models among this http URL http://candidates.our/ code is available at this URL https://github.com/Ewanwong/fairness_x_explainability
2025
Azime, Israel Abebe; Kanubala, Deborah D.; Afonja, Tejumade; Fritz, Mario; Valera, Isabel; Klakow, Dietrich; Slusallek, Philipp
Accept or Deny? Evaluating LLM Fairness and Performance in Loan Approval across Table-to-Text Serialization Approaches Bachelor Thesis
2025.
Abstract | Links | BibTeX | Tags: isabel, saml
@bachelorthesis{nokey,
title = {Accept or Deny? Evaluating LLM Fairness and Performance in Loan Approval across Table-to-Text Serialization Approaches},
author = {Israel Abebe Azime and Deborah D. Kanubala and Tejumade Afonja and Mario Fritz and Isabel Valera and Dietrich Klakow and Philipp Slusallek},
url = {https://arxiv.org/pdf/2508.21512},
year = {2025},
date = {2025-08-29},
urldate = {2025-08-29},
abstract = {Large Language Models (LLMs) are increasingly employed in high-stakes decision-making tasks, such as loan approvals. While their applications expand across domains, LLMs struggle to process tabular data, ensuring fairness and delivering reliable predictions. In this work, we assess the performance and fairness of LLMs on serialized loan approval datasets from three geographically distinct regions: Ghana, Germany, and the United States. Our evaluation focuses on the model’s zero-shot and in-context learning (ICL) capabilities. Our results reveal that the choice of serialization1 format significantly affects both performance and fairness in LLMs, with certain formats such as GReaT and LIFT yielding higher F1 scores but exacerbating fairness disparities. Notably, while ICL improved model performance by 4.9-59.6% relative to zero-shot baselines, its effect on fairness varied considerably across datasets. Our work underscores the importance of effective tabular data representation methods and fairness-aware models to improve the reliability of LLMs in financial decision-making},
keywords = {isabel, saml},
pubstate = {published},
tppubtype = {bachelorthesis}
}
Large Language Models (LLMs) are increasingly employed in high-stakes decision-making tasks, such as loan approvals. While their applications expand across domains, LLMs struggle to process tabular data, ensuring fairness and delivering reliable predictions. In this work, we assess the performance and fairness of LLMs on serialized loan approval datasets from three geographically distinct regions: Ghana, Germany, and the United States. Our evaluation focuses on the model’s zero-shot and in-context learning (ICL) capabilities. Our results reveal that the choice of serialization1 format significantly affects both performance and fairness in LLMs, with certain formats such as GReaT and LIFT yielding higher F1 scores but exacerbating fairness disparities. Notably, while ICL improved model performance by 4.9-59.6% relative to zero-shot baselines, its effect on fairness varied considerably across datasets. Our work underscores the importance of effective tabular data representation methods and fairness-aware models to improve the reliability of LLMs in financial decision-making
Eisenhut, Jan; Fivser, Daniel; Valera, Isabel; Hoffmann, J¨org
On Picking Good Policies: Leveraging Action-Policy Testing in Policy Training Journal Article
In: Proceedings of the International Conference on Automated Planning and Scheduling, 2025.
Abstract | Links | BibTeX | Tags: isabel
@article{Eisenhut2025OnPG,
title = {On Picking Good Policies: Leveraging Action-Policy Testing in Policy Training},
author = {Jan Eisenhut and Daniel Fivser and Isabel Valera and J¨org Hoffmann},
url = {https://api.semanticscholar.org/CorpusID:281347744},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {Proceedings of the International Conference on Automated Planning and Scheduling},
abstract = {Testing is a natural approach to assess the quality of learned action policies π. Prior work introduced policy testing in AI planning as searching for bugs in π, that is, states where π is sub-optimal with respect to a given testing objective. Beyond quality assurance, an obvious application of these methods is policy selection: given several π to choose from, we can use testing to select the "least buggy" one. Here, we integrate testing-based policy selection into the training process. This includes making more informed decisions when selecting the final policy after training, as well as choosing more promising intermediate policies during the training process. Our experiments with ASNets action policies show that integrating testing allows us to more reliably obtain good-quality policies.},
keywords = {isabel},
pubstate = {published},
tppubtype = {article}
}
Testing is a natural approach to assess the quality of learned action policies π. Prior work introduced policy testing in AI planning as searching for bugs in π, that is, states where π is sub-optimal with respect to a given testing objective. Beyond quality assurance, an obvious application of these methods is policy selection: given several π to choose from, we can use testing to select the "least buggy" one. Here, we integrate testing-based policy selection into the training process. This includes making more informed decisions when selecting the final policy after training, as well as choosing more promising intermediate policies during the training process. Our experiments with ASNets action policies show that integrating testing allows us to more reliably obtain good-quality policies.
Eniser, Hasan Ferit; Lin, Songtuan; Müller, Nicola; Isychev, Anastasia; Wüstholz, Valentin; Valera, Isabel; Hoffmann, J¨org; Christakis, Maria
Using Action-Policy Testing in RL to Reduce the Number of Bugs Journal Article
In: Proceedings of the International Symposium on Combinatorial Search, 2025.
Abstract | Links | BibTeX | Tags: isabel
@article{Eniser2025UsingAT,
title = {Using Action-Policy Testing in RL to Reduce the Number of Bugs},
author = {Hasan Ferit Eniser and Songtuan Lin and Nicola Müller and Anastasia Isychev and Valentin Wüstholz and Isabel Valera and J¨org Hoffmann and Maria Christakis},
url = {https://api.semanticscholar.org/CorpusID:280219509},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {Proceedings of the International Symposium on Combinatorial Search},
abstract = {Reinforcement learning is becoming ever more prominent in solving combinatorial search problems, in particular ones where states are images. Prior work has devised action-policy testing methodology, that identifies so-called bug states where policy performance is sub-optimal. Here we show how to leverage this methodology during the RL process, using action-policy testing to find bugs and injecting those as alternate start states for the training runs. Running experiments across six 2D games, we find that our testing-guided training often achieves similar expected reward while reducing the number of bugs.},
keywords = {isabel},
pubstate = {published},
tppubtype = {article}
}
Reinforcement learning is becoming ever more prominent in solving combinatorial search problems, in particular ones where states are images. Prior work has devised action-policy testing methodology, that identifies so-called bug states where policy performance is sub-optimal. Here we show how to leverage this methodology during the RL process, using action-policy testing to find bugs and injecting those as alternate start states for the training runs. Running experiments across six 2D games, we find that our testing-guided training often achieves similar expected reward while reducing the number of bugs.
Javaloy, Adrián; Vergari, Antonio; Valera, Isabel
COPA: Comparing the Incomparable to Explore the Pareto Front Journal Article
In: CoRR, vol. abs/2503.14321, 2025.
Abstract | Links | BibTeX | Tags: adrian, isabel, saml
@article{DBLP:journals/corr/abs-2503-14321,
title = {COPA: Comparing the Incomparable to Explore the Pareto Front},
author = {Adrián Javaloy and Antonio Vergari and Isabel Valera},
url = {https://doi.org/10.48550/arXiv.2503.14321},
doi = {10.48550/ARXIV.2503.14321},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {CoRR},
volume = {abs/2503.14321},
abstract = {In machine learning (ML), we often need to choose one among hundreds of trained ML models at hand, based on various objectives such as accuracy, robustness, fairness or scalability. However, it is often unclear how to compare, aggregate and, ultimately, trade-off these objectives, making it a time-consuming task that requires expert knowledge, as objectives may be measured in different units and scales. In this work, we investigate how objectives can be automatically normalized and aggregated to systematically help the user navigate their Pareto front. To this end, we make incomparable objectives comparable using their cumulative functions, approximated by their relative rankings. As a result, our proposed approach, COPA, can aggregate them while matching user-specific preferences, allowing practitioners to meaningfully navigate and search for models in the Pareto front. We demonstrate the potential impact of COPA in both model selection and benchmarking tasks across diverse ML areas such as fair ML, domain generalization, AutoML and foundation models, where classical ways to normalize and aggregate objectives fall short.},
keywords = {adrian, isabel, saml},
pubstate = {published},
tppubtype = {article}
}
In machine learning (ML), we often need to choose one among hundreds of trained ML models at hand, based on various objectives such as accuracy, robustness, fairness or scalability. However, it is often unclear how to compare, aggregate and, ultimately, trade-off these objectives, making it a time-consuming task that requires expert knowledge, as objectives may be measured in different units and scales. In this work, we investigate how objectives can be automatically normalized and aggregated to systematically help the user navigate their Pareto front. To this end, we make incomparable objectives comparable using their cumulative functions, approximated by their relative rankings. As a result, our proposed approach, COPA, can aggregate them while matching user-specific preferences, allowing practitioners to meaningfully navigate and search for models in the Pareto front. We demonstrate the potential impact of COPA in both model selection and benchmarking tasks across diverse ML areas such as fair ML, domain generalization, AutoML and foundation models, where classical ways to normalize and aggregate objectives fall short.
Almodóvar, Alejandro; Javaloy, Adrián; Parras, Juan; Zazo, Santiago; Valera, Isabel
DeCaFlow: A Deconfounding Causal Generative Model Journal Article Spotlight
In: CoRR, vol. abs/2503.15114, 2025.
Abstract | Links | BibTeX | Tags: adrian, isabel, saml, spotlight
@article{DBLP:journals/corr/abs-2503-15114,
title = {DeCaFlow: A Deconfounding Causal Generative Model},
author = {Alejandro Almodóvar and Adrián Javaloy and Juan Parras and Santiago Zazo and Isabel Valera},
url = {https://doi.org/10.48550/arXiv.2503.15114},
doi = {10.48550/ARXIV.2503.15114},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {CoRR},
volume = {abs/2503.15114},
abstract = {We introduce DeCaFlow, a deconfounding causal generative model. Training once per dataset using just observational data and the underlying causal graph, DeCaFlow enables accurate causal inference on continuous variables under the presence of hidden confounders. Specifically, we extend previous results on causal estimation under hidden confounding to show that a single instance of DeCaFlow provides correct estimates for all causal queries identifiable with do-calculus, leveraging proxy variables to adjust for the causal effects when do-calculus alone is insufficient. Moreover, we show that counterfactual queries are identifiable as long as their interventional counterparts are identifiable, and thus are also correctly estimated by DeCaFlow. Our empirical results on diverse settings (including the Ecoli70 dataset, with 3 independent hidden confounders, tens of observed variables and hundreds of causal queries) show that DeCaFlow outperforms existing approaches, while demonstrating its out-of-the-box applicability to any given causal graph},
keywords = {adrian, isabel, saml, spotlight},
pubstate = {published},
tppubtype = {article}
}
We introduce DeCaFlow, a deconfounding causal generative model. Training once per dataset using just observational data and the underlying causal graph, DeCaFlow enables accurate causal inference on continuous variables under the presence of hidden confounders. Specifically, we extend previous results on causal estimation under hidden confounding to show that a single instance of DeCaFlow provides correct estimates for all causal queries identifiable with do-calculus, leveraging proxy variables to adjust for the causal effects when do-calculus alone is insufficient. Moreover, we show that counterfactual queries are identifiable as long as their interventional counterparts are identifiable, and thus are also correctly estimated by DeCaFlow. Our empirical results on diverse settings (including the Ecoli70 dataset, with 3 independent hidden confounders, tens of observed variables and hundreds of causal queries) show that DeCaFlow outperforms existing approaches, while demonstrating its out-of-the-box applicability to any given causal graph
Cinquini, Martina; Beretta, Isacco; Ruggieri, Salvatore; Valera, Isabel
A Practical Approach to Causal Inference over Time Proceedings Article
In: Walsh, Toby; Shah, Julie; Kolter, Zico (Ed.): AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25 - March 4, 2025, Philadelphia, PA, USA, pp. 14832–14839, AAAI Press, 2025.
Abstract | Links | BibTeX | Tags: isabel, saml
@inproceedings{DBLP:conf/aaai/CinquiniBRV25,
title = {A Practical Approach to Causal Inference over Time},
author = {Martina Cinquini and Isacco Beretta and Salvatore Ruggieri and Isabel Valera},
editor = {Toby Walsh and Julie Shah and Zico Kolter},
url = {https://doi.org/10.1609/aaai.v39i14.33626},
doi = {10.1609/AAAI.V39I14.33626},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
booktitle = {AAAI-25, Sponsored by the Association for the Advancement of Artificial
Intelligence, February 25 - March 4, 2025, Philadelphia, PA, USA},
pages = {14832–14839},
publisher = {AAAI Press},
abstract = {In this paper, we focus on estimating the causal effect of an intervention over time on a dynamical system. To that end, we formally define causal interventions and their effects over time on discrete-time stochastic processes (DSPs). Then, we show under which conditions the equilibrium states of a DSP, both before and after a causal intervention, can be captured by a structural causal model (SCM). With such an equivalence at hand, we provide an explicit mapping from vector autoregressive models (VARs), broadly applied in econometrics, to linear, but potentially cyclic and/or affected by unmeasured confounders, SCMs. The resulting causal VAR framework allows us to perform causal inference over time from observational time series data. Our experiments on synthetic and real-world datasets show that the proposed framework achieves strong performance in terms of observational forecasting while enabling accurate estimation of the causal effect of interventions on dynamical systems. We demonstrate, through a case study, the potential practical questions that can be addressed using the proposed causal VAR framework.},
keywords = {isabel, saml},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we focus on estimating the causal effect of an intervention over time on a dynamical system. To that end, we formally define causal interventions and their effects over time on discrete-time stochastic processes (DSPs). Then, we show under which conditions the equilibrium states of a DSP, both before and after a causal intervention, can be captured by a structural causal model (SCM). With such an equivalence at hand, we provide an explicit mapping from vector autoregressive models (VARs), broadly applied in econometrics, to linear, but potentially cyclic and/or affected by unmeasured confounders, SCMs. The resulting causal VAR framework allows us to perform causal inference over time from observational time series data. Our experiments on synthetic and real-world datasets show that the proposed framework achieves strong performance in terms of observational forecasting while enabling accurate estimation of the causal effect of interventions on dynamical systems. We demonstrate, through a case study, the potential practical questions that can be addressed using the proposed causal VAR framework.
Peis, Ignacio; Koyuncu, Batuhan; Valera, Isabel; Frellsen, Jes
Hyper-Transforming Latent Diffusion Models Journal Article
In: CoRR, vol. abs/2504.16580, 2025.
Abstract | Links | BibTeX | Tags: batu, isabel, saml
@article{DBLP:journals/corr/abs-2504-16580,
title = {Hyper-Transforming Latent Diffusion Models},
author = {Ignacio Peis and Batuhan Koyuncu and Isabel Valera and Jes Frellsen},
url = {https://doi.org/10.48550/arXiv.2504.16580},
doi = {10.48550/ARXIV.2504.16580},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {CoRR},
volume = {abs/2504.16580},
abstract = {We introduce a novel generative framework for functions by integrating Implicit Neural Representations (INRs) and Transformer-based hypernetworks into latent variable models. Unlike prior approaches that rely on MLP-based hypernetworks with scalability limitations, our method employs a Transformer-based decoder to generate INR parameters from latent variables, addressing both representation capacity and computational efficiency. Our framework extends latent diffusion models (LDMs) to INR generation by replacing standard decoders with a Transformer-based hypernetwork, which can be trained either from scratch or via hyper-transforming: a strategy that fine-tunes only the decoder while freezing the pre-trained latent space. This enables efficient adaptation of existing generative models to INR-based representations without requiring full retraining. We validate our approach across multiple modalities, demonstrating improved scalability, expressiveness, and generalization over existing INR-based generative models. Our findings establish a unified and flexible framework for learning structured function representations.},
keywords = {batu, isabel, saml},
pubstate = {published},
tppubtype = {article}
}
We introduce a novel generative framework for functions by integrating Implicit Neural Representations (INRs) and Transformer-based hypernetworks into latent variable models. Unlike prior approaches that rely on MLP-based hypernetworks with scalability limitations, our method employs a Transformer-based decoder to generate INR parameters from latent variables, addressing both representation capacity and computational efficiency. Our framework extends latent diffusion models (LDMs) to INR generation by replacing standard decoders with a Transformer-based hypernetwork, which can be trained either from scratch or via hyper-transforming: a strategy that fine-tunes only the decoder while freezing the pre-trained latent space. This enables efficient adaptation of existing generative models to INR-based representations without requiring full retraining. We validate our approach across multiple modalities, demonstrating improved scalability, expressiveness, and generalization over existing INR-based generative models. Our findings establish a unified and flexible framework for learning structured function representations.
Koyuncu, Batuhan; DeVries, Rachael; Winther, Ole; Valera, Isabel
Temporal Variational Implicit Neural Representations Journal Article
In: CoRR, vol. abs/2506.01544, 2025.
Abstract | Links | BibTeX | Tags: batu, isabel
@article{DBLP:journals/corr/abs-2506-01544,
title = {Temporal Variational Implicit Neural Representations},
author = {Batuhan Koyuncu and Rachael DeVries and Ole Winther and Isabel Valera},
url = {https://doi.org/10.48550/arXiv.2506.01544},
doi = {10.48550/ARXIV.2506.01544},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {CoRR},
volume = {abs/2506.01544},
abstract = {We introduce Temporal Variational Implicit Neural Representations (TV-INRs), a probabilistic framework for modeling irregular multivariate time series that enables efficient individualized imputation and forecasting. By integrating implicit neural representations with latent variable models, TV-INRs learn distributions over time-continuous generator functions conditioned on signal-specific covariates. Unlike existing approaches that require extensive training, fine-tuning or meta-learning, our method achieves accurate individualized predictions through a single forward pass. Our experiments demonstrate that with a single TV-INRs instance, we can accurately solve diverse imputation and forecasting tasks, offering a computationally efficient and scalable solution for real-world applications. TV-INRs excel especially in low-data regimes, where it outperforms existing methods by an order of magnitude in mean squared error for imputation task.},
keywords = {batu, isabel},
pubstate = {published},
tppubtype = {article}
}
We introduce Temporal Variational Implicit Neural Representations (TV-INRs), a probabilistic framework for modeling irregular multivariate time series that enables efficient individualized imputation and forecasting. By integrating implicit neural representations with latent variable models, TV-INRs learn distributions over time-continuous generator functions conditioned on signal-specific covariates. Unlike existing approaches that require extensive training, fine-tuning or meta-learning, our method achieves accurate individualized predictions through a single forward pass. Our experiments demonstrate that with a single TV-INRs instance, we can accurately solve diverse imputation and forecasting tasks, offering a computationally efficient and scalable solution for real-world applications. TV-INRs excel especially in low-data regimes, where it outperforms existing methods by an order of magnitude in mean squared error for imputation task.
Kalampalikis, Nektarios; Gupta, Kavya; Vitanov, Georgi; Valera, Isabel
Towards Reasonable Concept Bottleneck Models Journal Article
In: CoRR, vol. abs/2506.05014, 2025.
Abstract | Links | BibTeX | Tags: isabel, kavya, nektarios, saml
@article{DBLP:journals/corr/abs-2506-05014,
title = {Towards Reasonable Concept Bottleneck Models},
author = {Nektarios Kalampalikis and Kavya Gupta and Georgi Vitanov and Isabel Valera},
url = {https://doi.org/10.48550/arXiv.2506.05014},
doi = {10.48550/ARXIV.2506.05014},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {CoRR},
volume = {abs/2506.05014},
abstract = {In this paper, we propose textbf{C}oncept textbf{REA}soning textbf{M}odels (CREAM), a novel family of Concept Bottleneck Models (CBMs) that: (i) explicitly encodes concept-concept ({texttt{C-C}}) and concept-task ({texttt{C$rightarrow$Y}}) relationships to enforce a desired model reasoning; and (ii) use a regularized side-channel to achieve competitive task performance, while keeping high concept importance. Specifically, CREAM architecturally embeds (bi)directed concept-concept, and concept to task relationships specified by a human expert, while severing undesired information flows (e.g., to handle mutually exclusive concepts). Moreover, CREAM integrates a black-box side-channel that is regularized to encourage task predictions to be grounded in the relevant concepts, thereby utilizing the side-channel only when necessary to enhance performance. Our experiments show that: (i) CREAM mainly relies on concepts while achieving task performance on par with black-box models; and (ii) the embedded {texttt{C-C}} and {texttt{C$rightarrow$Y}} relationships ease model interventions and mitigate concept leakage.},
keywords = {isabel, kavya, nektarios, saml},
pubstate = {published},
tppubtype = {article}
}
In this paper, we propose textbf{C}oncept textbf{REA}soning textbf{M}odels (CREAM), a novel family of Concept Bottleneck Models (CBMs) that: (i) explicitly encodes concept-concept ({texttt{C-C}}) and concept-task ({texttt{C$rightarrow$Y}}) relationships to enforce a desired model reasoning; and (ii) use a regularized side-channel to achieve competitive task performance, while keeping high concept importance. Specifically, CREAM architecturally embeds (bi)directed concept-concept, and concept to task relationships specified by a human expert, while severing undesired information flows (e.g., to handle mutually exclusive concepts). Moreover, CREAM integrates a black-box side-channel that is regularized to encourage task predictions to be grounded in the relevant concepts, thereby utilizing the side-channel only when necessary to enhance performance. Our experiments show that: (i) CREAM mainly relies on concepts while achieving task performance on par with black-box models; and (ii) the embedded {texttt{C-C}} and {texttt{C$rightarrow$Y}} relationships ease model interventions and mitigate concept leakage.
Azime, Israel Abebe; Kanubala, Deborah Dormah; Afonja, Tejumade; Fritz, Mario; Valera, Isabel; Klakow, Dietrich; Slusallek, Philipp
Accept or Deny? Evaluating LLM Fairness and Performance in Loan Approval across Table-to-Text Serialization Approaches Journal Article
In: CoRR, vol. abs/2508.21512, 2025.
Abstract | Links | BibTeX | Tags: deborah, isabel
@article{DBLP:journals/corr/abs-2508-21512,
title = {Accept or Deny? Evaluating LLM Fairness and Performance in Loan Approval across Table-to-Text Serialization Approaches},
author = {Israel Abebe Azime and Deborah Dormah Kanubala and Tejumade Afonja and Mario Fritz and Isabel Valera and Dietrich Klakow and Philipp Slusallek},
url = {https://doi.org/10.48550/arXiv.2508.21512},
doi = {10.48550/ARXIV.2508.21512},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {CoRR},
volume = {abs/2508.21512},
abstract = {Large Language Models (LLMs) are increasingly employed in high-stakes decision-making tasks, such as loan approvals. While their applications expand across domains, LLMs struggle to process tabular data, ensuring fairness and delivering reliable predictions. In this work, we assess the performance and fairness of LLMs on serialized loan approval datasets from three geographically distinct regions: Ghana, Germany, and the United States. Our evaluation focuses on the model’s zero-shot and in-context learning (ICL) capabilities. Our results reveal that the choice of serialization format significantly affects both performance and fairness in LLMs, with certain formats such as GReaT and LIFT yielding higher F1 scores but exacerbating fairness disparities. Notably, while ICL improved model performance by 4.9-59.6% relative to zero-shot baselines, its effect on fairness varied considerably across datasets. Our work underscores the importance of effective tabular data representation methods and fairness-aware models to improve the reliability of LLMs in financial decision-making.},
keywords = {deborah, isabel},
pubstate = {published},
tppubtype = {article}
}
Large Language Models (LLMs) are increasingly employed in high-stakes decision-making tasks, such as loan approvals. While their applications expand across domains, LLMs struggle to process tabular data, ensuring fairness and delivering reliable predictions. In this work, we assess the performance and fairness of LLMs on serialized loan approval datasets from three geographically distinct regions: Ghana, Germany, and the United States. Our evaluation focuses on the model’s zero-shot and in-context learning (ICL) capabilities. Our results reveal that the choice of serialization format significantly affects both performance and fairness in LLMs, with certain formats such as GReaT and LIFT yielding higher F1 scores but exacerbating fairness disparities. Notably, while ICL improved model performance by 4.9-59.6% relative to zero-shot baselines, its effect on fairness varied considerably across datasets. Our work underscores the importance of effective tabular data representation methods and fairness-aware models to improve the reliability of LLMs in financial decision-making.
Gros, Timo P.; Müller, Nicola J.; Fiser, Daniel; Valera, Isabel; Wolf, Verena; Hoffmann, Jörg
Per-Domain Generalizing Policies: On Validation Instances and Scaling Behavior Journal Article
In: CoRR, vol. abs/2505.00439, 2025.
Abstract | Links | BibTeX | Tags: isabel
@article{DBLP:journals/corr/abs-2505-00439,
title = {Per-Domain Generalizing Policies: On Validation Instances and Scaling Behavior},
author = {Timo P. Gros and Nicola J. Müller and Daniel Fiser and Isabel Valera and Verena Wolf and Jörg Hoffmann},
url = {https://doi.org/10.48550/arXiv.2505.00439},
doi = {10.48550/ARXIV.2505.00439},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {CoRR},
volume = {abs/2505.00439},
abstract = {Recent work has shown that successful per-domain generalizing action policies can be learned. Scaling behavior, from small training instances to large test instances, is the key objective; and the use of validation instances larger than training instances is one key to achieve it. Prior work has used fixed validation sets. Here, we introduce a method generating the validation set dynamically, on the fly, increasing instance size so long as informative and this http://feasible.we/ also introduce refined methodology for evaluating scaling behavior, generating test instances systematically to guarantee a given confidence in coverage performance for each instance size. In experiments, dynamic validation improves scaling behavior of GNN policies in all 9 domains used.},
keywords = {isabel},
pubstate = {published},
tppubtype = {article}
}
Recent work has shown that successful per-domain generalizing action policies can be learned. Scaling behavior, from small training instances to large test instances, is the key objective; and the use of validation instances larger than training instances is one key to achieve it. Prior work has used fixed validation sets. Here, we introduce a method generating the validation set dynamically, on the fly, increasing instance size so long as informative and this http://feasible.we/ also introduce refined methodology for evaluating scaling behavior, generating test instances systematically to guarantee a given confidence in coverage performance for each instance size. In experiments, dynamic validation improves scaling behavior of GNN policies in all 9 domains used.
Kanubala, Deborah Dormah; Valera, Isabel
On the Misalignment Between Legal Notions and Statistical Metrics of Intersectional Fairness Journal Article
In: Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 2025.
Abstract | Links | BibTeX | Tags: deborah, isabel, saml
@article{Kanubala2025OnTM,
title = {On the Misalignment Between Legal Notions and Statistical Metrics of Intersectional Fairness},
author = {Deborah Dormah Kanubala and Isabel Valera},
url = {https://api.semanticscholar.org/CorpusID:282175621},
year = {2025},
date = {2025-01-01},
urldate = {2025-01-01},
journal = {Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society},
abstract = {Intersectional (un)fairness, as conceptualized in legal and social theory, emphasizes the non-additive and structurally complex nature of discrimination against individuals at the intersection of multiple sensitive attributes (such as race, gender, etc). Recent works have proposed statistical metrics for intersectional fairness by estimating disparities across groups of individuals sharing two or more sensitive attributes. However, it is unclear if these metrics detect uniquely intersectional discrimination. We therefore pose the following question, Do current statistical intersectional metrics detect the non-additive discrimination highlighted by intersectionality theory? More specifically, to answer this, we run controlled synthetic data experiments that explicitly allow us to control for single, multiple, intersectional, and compounded forms of discrimination. Our analyses show that current statistical metrics for intersectional fairness behave more like multi-attribute disparity measures. Specifically, they respond more strongly to additive or compounded biases than to non-additive interaction effects. While they effectively capture disparities across multiple sensitive attributes, they often fail to detect uniquely intersectional discrimination. These findings reveal a fundamental misalignment between existing intersectional fairness metrics and the legal and theoretical foundations of intersectionality. We argue that if intersectional fairness metrics are to be deemed truly intersectional, they must be explicitly designed to account for the structural, non-additive nature of intersectional discrimination.},
keywords = {deborah, isabel, saml},
pubstate = {published},
tppubtype = {article}
}
Intersectional (un)fairness, as conceptualized in legal and social theory, emphasizes the non-additive and structurally complex nature of discrimination against individuals at the intersection of multiple sensitive attributes (such as race, gender, etc). Recent works have proposed statistical metrics for intersectional fairness by estimating disparities across groups of individuals sharing two or more sensitive attributes. However, it is unclear if these metrics detect uniquely intersectional discrimination. We therefore pose the following question, Do current statistical intersectional metrics detect the non-additive discrimination highlighted by intersectionality theory? More specifically, to answer this, we run controlled synthetic data experiments that explicitly allow us to control for single, multiple, intersectional, and compounded forms of discrimination. Our analyses show that current statistical metrics for intersectional fairness behave more like multi-attribute disparity measures. Specifically, they respond more strongly to additive or compounded biases than to non-additive interaction effects. While they effectively capture disparities across multiple sensitive attributes, they often fail to detect uniquely intersectional discrimination. These findings reveal a fundamental misalignment between existing intersectional fairness metrics and the legal and theoretical foundations of intersectionality. We argue that if intersectional fairness metrics are to be deemed truly intersectional, they must be explicitly designed to account for the structural, non-additive nature of intersectional discrimination.
2024
Beretta, Isacco; Cinquini, Martina; Valera, Isabel
Enhancing Fairness Through Time-aware Recourse: a Pathway to Realistic Algorithmic Recommendations Proceedings Article
In: Cerrato, Mattia; Coronel, Alesia Vallenas; Ahrweiler, Petra; Loi, Michele; Pechenizkiy, Mykola; Tamò-Larrieux, Aurelia (Ed.): Proceedings of the 3rd European Workshop on Algorithmic Fairness, Mainz, Germany, July 1st to 3rd, 2024, CEUR-WS.org, 2024.
Abstract | Links | BibTeX | Tags: isabel
@inproceedings{DBLP:conf/ewaf/BerettaCV24,
title = {Enhancing Fairness Through Time-aware Recourse: a Pathway to Realistic Algorithmic Recommendations},
author = {Isacco Beretta and Martina Cinquini and Isabel Valera},
editor = {Mattia Cerrato and Alesia Vallenas Coronel and Petra Ahrweiler and Michele Loi and Mykola Pechenizkiy and Aurelia Tamò-Larrieux},
url = {https://ceur-ws.org/Vol-3908/paper_10.pdf},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
booktitle = {Proceedings of the 3rd European Workshop on Algorithmic Fairness,
Mainz, Germany, July 1st to 3rd, 2024},
volume = {3908},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
abstract = {Algorithmic Recourse (AR) addresses adverse outcomes in automated decision-making by offering actionable recommendations. However, current state-of-the-art methods overlook the interdependence of features and do not consider the temporal dimension. To fill this gap, time-car emerges as a pioneering approach that integrates temporal information. Building upon this formulation, this work investigates the context of fairness, specifically focusing on the implications for marginalized demographic groups. Since long wait times can significantly impact communities’ financial, educational, and personal lives, exploring how time-related factors affect the fair treatment of these groups is crucial to suggest potential
solutions to reduce the negative effects on minority populations. Our findings set the stage for more equitable AR techniques sensitive to individual needs, ultimately fostering fairer suggestions.},
keywords = {isabel},
pubstate = {published},
tppubtype = {inproceedings}
}
Algorithmic Recourse (AR) addresses adverse outcomes in automated decision-making by offering actionable recommendations. However, current state-of-the-art methods overlook the interdependence of features and do not consider the temporal dimension. To fill this gap, time-car emerges as a pioneering approach that integrates temporal information. Building upon this formulation, this work investigates the context of fairness, specifically focusing on the implications for marginalized demographic groups. Since long wait times can significantly impact communities’ financial, educational, and personal lives, exploring how time-related factors affect the fair treatment of these groups is crucial to suggest potential
solutions to reduce the negative effects on minority populations. Our findings set the stage for more equitable AR techniques sensitive to individual needs, ultimately fostering fairer suggestions.
solutions to reduce the negative effects on minority populations. Our findings set the stage for more equitable AR techniques sensitive to individual needs, ultimately fostering fairer suggestions.
Kanubala, Deborah Dormah; Valera, Isabel; Gupta, Kavya
Fairness Beyond Binary Decisions: a Case Study on German Credit Proceedings Article
In: Cerrato, Mattia; Coronel, Alesia Vallenas; Ahrweiler, Petra; Loi, Michele; Pechenizkiy, Mykola; Tamò-Larrieux, Aurelia (Ed.): Proceedings of the 3rd European Workshop on Algorithmic Fairness, Mainz, Germany, July 1st to 3rd, 2024, CEUR-WS.org, 2024.
Abstract | Links | BibTeX | Tags: deborah, isabel, kavya, saml
@inproceedings{DBLP:conf/ewaf/KanubalaVG24,
title = {Fairness Beyond Binary Decisions: a Case Study on German Credit},
author = {Deborah Dormah Kanubala and Isabel Valera and Kavya Gupta},
editor = {Mattia Cerrato and Alesia Vallenas Coronel and Petra Ahrweiler and Michele Loi and Mykola Pechenizkiy and Aurelia Tamò-Larrieux},
url = {https://ceur-ws.org/Vol-3908/paper_15.pdf},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
booktitle = {Proceedings of the 3rd European Workshop on Algorithmic Fairness,
Mainz, Germany, July 1st to 3rd, 2024},
volume = {3908},
publisher = {CEUR-WS.org},
series = {CEUR Workshop Proceedings},
abstract = {Data-driven approaches are increasingly used to (partially) automate decision-making in credit scoring
by predicting whether an applicant is “creditworthy or not” based on a set of features about the applicant,
such as age and income, along with what we refer here to as treatment decisions, e.g., loan amount and
duration. Existing data-driven approaches for automating and evaluating the accuracy and fairness of
such credit decisions ignore that treatment decisions (here, loan terms) are part of the decision and
thus may be subject to discrimination. This discrimination can propagate to the final outcome (repaid
or not) of positive decisions (granted loans). In this extended abstract, we rely on causal reasoning
and a broadly studied fair machine-learning dataset, the German credit, to i) show that the current fair
data-driven approach neglects discrimination in treatment decisions (i.e., loan terms) and its downstream
consequences on the decision outcome (i.e., ability to repay); and ii) argue for the need to move beyond
binary decisions in fair data-driven decision-making in consequential settings like credit scoring},
keywords = {deborah, isabel, kavya, saml},
pubstate = {published},
tppubtype = {inproceedings}
}
Data-driven approaches are increasingly used to (partially) automate decision-making in credit scoring
by predicting whether an applicant is “creditworthy or not” based on a set of features about the applicant,
such as age and income, along with what we refer here to as treatment decisions, e.g., loan amount and
duration. Existing data-driven approaches for automating and evaluating the accuracy and fairness of
such credit decisions ignore that treatment decisions (here, loan terms) are part of the decision and
thus may be subject to discrimination. This discrimination can propagate to the final outcome (repaid
or not) of positive decisions (granted loans). In this extended abstract, we rely on causal reasoning
and a broadly studied fair machine-learning dataset, the German credit, to i) show that the current fair
data-driven approach neglects discrimination in treatment decisions (i.e., loan terms) and its downstream
consequences on the decision outcome (i.e., ability to repay); and ii) argue for the need to move beyond
binary decisions in fair data-driven decision-making in consequential settings like credit scoring
by predicting whether an applicant is “creditworthy or not” based on a set of features about the applicant,
such as age and income, along with what we refer here to as treatment decisions, e.g., loan amount and
duration. Existing data-driven approaches for automating and evaluating the accuracy and fairness of
such credit decisions ignore that treatment decisions (here, loan terms) are part of the decision and
thus may be subject to discrimination. This discrimination can propagate to the final outcome (repaid
or not) of positive decisions (granted loans). In this extended abstract, we rely on causal reasoning
and a broadly studied fair machine-learning dataset, the German credit, to i) show that the current fair
data-driven approach neglects discrimination in treatment decisions (i.e., loan terms) and its downstream
consequences on the decision outcome (i.e., ability to repay); and ii) argue for the need to move beyond
binary decisions in fair data-driven decision-making in consequential settings like credit scoring
Sánchez-Martin, Pablo; Utz, Sonja; Valera, Isabel
Exploring the Boundaries of Ambient Awareness in Twitter Journal Article
In: CoRR, vol. abs/2403.17776, 2024.
Abstract | Links | BibTeX | Tags: isabel, pablo
@article{DBLP:journals/corr/abs-2403-17776,
title = {Exploring the Boundaries of Ambient Awareness in Twitter},
author = {Pablo Sánchez-Martin and Sonja Utz and Isabel Valera},
url = {https://doi.org/10.48550/arXiv.2403.17776},
doi = {10.48550/ARXIV.2403.17776},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
journal = {CoRR},
volume = {abs/2403.17776},
abstract = {Ambient awareness refers to the ability of social media users to obtain knowledge about who knows what (i.e., users' expertise) in their network, by simply being exposed to other users' content (e.g, tweets on Twitter). Previous work, based on user surveys, reveals that individuals self-report ambient awareness only for parts of their networks. However, it is unclear whether it is their limited cognitive capacity or the limited exposure to diagnostic tweets (i.e., online content) that prevents people from developing ambient awareness for their complete network. In this work, we focus on in-wall ambient awareness (IWAA) in Twitter and conduct a two-step data-driven analysis, that allows us to explore to which extent IWAA is likely, or even possible. First, we rely on reactions (e.g., likes), as strong evidence of users being aware of experts in Twitter. Unfortunately, such strong evidence can be only measured for active users, which represent the minority in the network. Thus to study the boundaries of IWAA to a larger extent, in the second part of our analysis, we instead focus on the passive exposure to content generated by other users -- which we refer to as in-wall visibility. This analysis shows that (in line with citet{levordashka2016ambient}) only for a subset of users IWAA is plausible, while for the majority it is unlikely, if even possible, to develop IWAA. We hope that our methodology paves the way for the emergence of data-driven approaches for the study of ambient awareness.},
keywords = {isabel, pablo},
pubstate = {published},
tppubtype = {article}
}
Ambient awareness refers to the ability of social media users to obtain knowledge about who knows what (i.e., users' expertise) in their network, by simply being exposed to other users' content (e.g, tweets on Twitter). Previous work, based on user surveys, reveals that individuals self-report ambient awareness only for parts of their networks. However, it is unclear whether it is their limited cognitive capacity or the limited exposure to diagnostic tweets (i.e., online content) that prevents people from developing ambient awareness for their complete network. In this work, we focus on in-wall ambient awareness (IWAA) in Twitter and conduct a two-step data-driven analysis, that allows us to explore to which extent IWAA is likely, or even possible. First, we rely on reactions (e.g., likes), as strong evidence of users being aware of experts in Twitter. Unfortunately, such strong evidence can be only measured for active users, which represent the minority in the network. Thus to study the boundaries of IWAA to a larger extent, in the second part of our analysis, we instead focus on the passive exposure to content generated by other users -- which we refer to as in-wall visibility. This analysis shows that (in line with citet{levordashka2016ambient}) only for a subset of users IWAA is plausible, while for the majority it is unlikely, if even possible, to develop IWAA. We hope that our methodology paves the way for the emergence of data-driven approaches for the study of ambient awareness.
Sánchez-Martin, Pablo; Khan, Kinaan Aamir; Valera, Isabel
Improving the interpretability of GNN predictions through conformal-based graph sparsification Journal Article
In: CoRR, vol. abs/2404.12356, 2024.
Abstract | Links | BibTeX | Tags: isabel, pablo
@article{DBLP:journals/corr/abs-2404-12356,
title = {Improving the interpretability of GNN predictions through conformal-based graph sparsification},
author = {Pablo Sánchez-Martin and Kinaan Aamir Khan and Isabel Valera},
url = {https://doi.org/10.48550/arXiv.2404.12356},
doi = {10.48550/ARXIV.2404.12356},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
journal = {CoRR},
volume = {abs/2404.12356},
abstract = {Graph Neural Networks (GNNs) have achieved state-of-the-art performance in solving graph classification tasks. However, most GNN architectures aggregate information from all nodes and edges in a graph, regardless of their relevance to the task at hand, thus hindering the interpretability of their predictions. In contrast to prior work, in this paper we propose a GNN emph{training} approach that jointly i) finds the most predictive subgraph by removing edges and/or nodes -- -emph{without making assumptions about the subgraph structure} -- while ii) optimizing the performance of the graph classification task. To that end, we rely on reinforcement learning to solve the resulting bi-level optimization with a reward function based on conformal predictions to account for the current in-training uncertainty of the classifier. Our empirical results on nine different graph classification datasets show that our method competes in performance with baselines while relying on significantly sparser subgraphs, leading to more interpretable GNN-based predictions.},
keywords = {isabel, pablo},
pubstate = {published},
tppubtype = {article}
}
Graph Neural Networks (GNNs) have achieved state-of-the-art performance in solving graph classification tasks. However, most GNN architectures aggregate information from all nodes and edges in a graph, regardless of their relevance to the task at hand, thus hindering the interpretability of their predictions. In contrast to prior work, in this paper we propose a GNN emph{training} approach that jointly i) finds the most predictive subgraph by removing edges and/or nodes -- -emph{without making assumptions about the subgraph structure} -- while ii) optimizing the performance of the graph classification task. To that end, we rely on reinforcement learning to solve the resulting bi-level optimization with a reward function based on conformal predictions to account for the current in-training uncertainty of the classifier. Our empirical results on nine different graph classification datasets show that our method competes in performance with baselines while relying on significantly sparser subgraphs, leading to more interpretable GNN-based predictions.
Rateike, Miriam; Valera, Isabel; Forré, Patrick
Designing Long-term Group Fair Policies in Dynamical Systems Proceedings Article
In: The 2024 ACM Conference on Fairness, Accountability, and Transparency, FAccT 2024, Rio de Janeiro, Brazil, June 3-6, 2024, pp. 20–50, ACM, 2024.
Abstract | Links | BibTeX | Tags: isabel, saml
@inproceedings{DBLP:conf/fat/RateikeVF24,
title = {Designing Long-term Group Fair Policies in Dynamical Systems},
author = {Miriam Rateike and Isabel Valera and Patrick Forré},
url = {https://doi.org/10.1145/3630106.3658538},
doi = {10.1145/3630106.3658538},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
booktitle = {The 2024 ACM Conference on Fairness, Accountability, and Transparency,
FAccT 2024, Rio de Janeiro, Brazil, June 3-6, 2024},
pages = {20–50},
publisher = {ACM},
abstract = {Neglecting the effect that decisions have on individuals (and thus, on the underlying data distribution) when designing algorithmic decision-making policies may increase inequalities and unfairness in the long term—even if fairness considerations were taken into account in the policy design process. In this paper, we propose a novel framework for studying long-term group fairness in dynamical systems, in which current decisions may affect an individual’s features in the next step, and thus, future decisions. Specifically, our framework allows us to identify a time-independent policy that converges, if deployed, to the targeted fair stationary state of the system in the long-term, independently of the initial data distribution. We model the system dynamics with a time-homogeneous Markov chain and optimize the policy leveraging the Markov Chain Convergence Theorem to ensure unique convergence. Our framework enables the utilization of historical temporal data to tackle challenges associated with delayed feedback when learning long-term fair policies in practice. Importantly, our framework shows that interventions on the data distribution (e.g., subsidies) can be used to achieve policy learning that is both short- and long-term fair. We provide examples of different targeted fair states of the system, encompassing a range of long-term goals for society and policymakers. In semi-synthetic simulations based on real-world datasets, we show how our approach facilitates identifying effective interventions for long-term fairness.},
keywords = {isabel, saml},
pubstate = {published},
tppubtype = {inproceedings}
}
Neglecting the effect that decisions have on individuals (and thus, on the underlying data distribution) when designing algorithmic decision-making policies may increase inequalities and unfairness in the long term—even if fairness considerations were taken into account in the policy design process. In this paper, we propose a novel framework for studying long-term group fairness in dynamical systems, in which current decisions may affect an individual’s features in the next step, and thus, future decisions. Specifically, our framework allows us to identify a time-independent policy that converges, if deployed, to the targeted fair stationary state of the system in the long-term, independently of the initial data distribution. We model the system dynamics with a time-homogeneous Markov chain and optimize the policy leveraging the Markov Chain Convergence Theorem to ensure unique convergence. Our framework enables the utilization of historical temporal data to tackle challenges associated with delayed feedback when learning long-term fair policies in practice. Importantly, our framework shows that interventions on the data distribution (e.g., subsidies) can be used to achieve policy learning that is both short- and long-term fair. We provide examples of different targeted fair states of the system, encompassing a range of long-term goals for society and policymakers. In semi-synthetic simulations based on real-world datasets, we show how our approach facilitates identifying effective interventions for long-term fairness.
Majumdar, Ayan; Valera, Isabel
CARMA: A practical framework to generate recommendations for causal algorithmic recourse at scale Proceedings Article
In: The 2024 ACM Conference on Fairness, Accountability, and Transparency, FAccT 2024, Rio de Janeiro, Brazil, June 3-6, 2024, pp. 1745–1762, ACM, 2024.
Abstract | Links | BibTeX | Tags: ayanm, isabel
@inproceedings{DBLP:conf/fat/MajumdarV24,
title = {CARMA: A practical framework to generate recommendations for causal algorithmic recourse at scale},
author = {Ayan Majumdar and Isabel Valera},
url = {https://doi.org/10.1145/3630106.3659003},
doi = {10.1145/3630106.3659003},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
booktitle = {The 2024 ACM Conference on Fairness, Accountability, and Transparency,
FAccT 2024, Rio de Janeiro, Brazil, June 3-6, 2024},
pages = {1745–1762},
publisher = {ACM},
abstract = {Algorithms are increasingly used to automate large-scale decision-making processes, e.g., online platforms that make instant decisions in lending, hiring, and education. When such automated systems yield unfavorable decisions, it is imperative to allow for recourse by accompanying the instantaneous negative decisions with recommendations that can help affected individuals to overturn them. However, the practical challenges of providing algorithmic recourse in large-scale settings are not negligible: giving recourse recommendations that are actionable requires not only causal knowledge of the relationships between applicant features but also solving a complex combinatorial optimization problem for each rejected applicant. In this work, we introduce CARMA, a novel framework to generate causal recourse recommendations at scale. For practical settings with limited causal information, CARMA leverages pre-trained state-of-the-art causal generative models to find recourse recommendations. More importantly, CARMA addresses the scalability of finding these recommendations by casting the complex recourse optimization problem as a prediction task. By training a novel neural-network-based framework, CARMA efficiently solves the prediction task without requiring supervision for optimal recourse actions. Our extensive evaluations show that post-training, running inference on CARMA reliably amortizes causal recourse, generating optimal and instantaneous recommendations. CARMA exhibits flexibility, as its optimization is versatile with respect to the algorithmic decision-making and pre-trained causal generative models, provided their differentiability is ensured. Furthermore, we showcase CARMA in a case study, illustrating its ability to tailor causal recourse recommendations by readily incorporating population-level feature preferences based on factors such as difficulty or time needed.},
keywords = {ayanm, isabel},
pubstate = {published},
tppubtype = {inproceedings}
}
Algorithms are increasingly used to automate large-scale decision-making processes, e.g., online platforms that make instant decisions in lending, hiring, and education. When such automated systems yield unfavorable decisions, it is imperative to allow for recourse by accompanying the instantaneous negative decisions with recommendations that can help affected individuals to overturn them. However, the practical challenges of providing algorithmic recourse in large-scale settings are not negligible: giving recourse recommendations that are actionable requires not only causal knowledge of the relationships between applicant features but also solving a complex combinatorial optimization problem for each rejected applicant. In this work, we introduce CARMA, a novel framework to generate causal recourse recommendations at scale. For practical settings with limited causal information, CARMA leverages pre-trained state-of-the-art causal generative models to find recourse recommendations. More importantly, CARMA addresses the scalability of finding these recommendations by casting the complex recourse optimization problem as a prediction task. By training a novel neural-network-based framework, CARMA efficiently solves the prediction task without requiring supervision for optimal recourse actions. Our extensive evaluations show that post-training, running inference on CARMA reliably amortizes causal recourse, generating optimal and instantaneous recommendations. CARMA exhibits flexibility, as its optimization is versatile with respect to the algorithmic decision-making and pre-trained causal generative models, provided their differentiability is ensured. Furthermore, we showcase CARMA in a case study, illustrating its ability to tailor causal recourse recommendations by readily incorporating population-level feature preferences based on factors such as difficulty or time needed.
Wu, Nan; Valera, Isabel; Sinz, Fabian H.; Ecker, Alexander S.; Euler, Thomas; Qiu, Yongrong
Probabilistic neural transfer function estimation with Bayesian system identification Journal Article
In: PLoS Comput. Biol., vol. 20, no. 7, pp. 1012354, 2024.
Abstract | Links | BibTeX | Tags: isabel
@article{DBLP:journals/ploscb/WuVSEEQ24,
title = {Probabilistic neural transfer function estimation with Bayesian system identification},
author = {Nan Wu and Isabel Valera and Fabian H. Sinz and Alexander S. Ecker and Thomas Euler and Yongrong Qiu},
url = {https://doi.org/10.1371/journal.pcbi.1012354},
doi = {10.1371/JOURNAL.PCBI.1012354},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
journal = {PLoS Comput. Biol.},
volume = {20},
number = {7},
pages = {1012354},
abstract = {Neural population responses in sensory systems are driven by external physical stimuli. This stimulus-response relationship is typically characterized by receptive fields, which have been estimated by neural system identification approaches. Such models usually require a large amount of training data, yet, the recording time for animal experiments is limited, giving rise to epistemic uncertainty for the learned neural transfer functions. While deep neural network models have demonstrated excellent power on neural prediction, they usually do not provide the uncertainty of the resulting neural representations and derived statistics, such as most exciting inputs (MEIs), from in silico experiments. Here, we present a Bayesian system identification approach to predict neural responses to visual stimuli, and explore whether explicitly modeling network weight variability can be beneficial for identifying neural response properties. To this end, we use variational inference to estimate the posterior distribution of each model weight given the training data. Tests with different neural datasets demonstrate that this method can achieve higher or comparable performance on neural prediction, with a much higher data efficiency compared to Monte Carlo dropout methods and traditional models using point estimates of the model parameters. At the same time, our variational method provides us with an effectively infinite ensemble, avoiding the idiosyncrasy of any single model, to generate MEIs. This allows us to estimate the uncertainty of stimulus-response function, which we have found to be negatively correlated with the predictive performance at model level and may serve to evaluate models. Furthermore, our approach enables us to identify response properties with credible intervals and to determine whether the inferred features are meaningful by performing statistical tests on MEIs. Finally, in silico experiments show that our model generates stimuli driving neuronal activity significantly better than traditional models in the limited-data regime.},
keywords = {isabel},
pubstate = {published},
tppubtype = {article}
}
Neural population responses in sensory systems are driven by external physical stimuli. This stimulus-response relationship is typically characterized by receptive fields, which have been estimated by neural system identification approaches. Such models usually require a large amount of training data, yet, the recording time for animal experiments is limited, giving rise to epistemic uncertainty for the learned neural transfer functions. While deep neural network models have demonstrated excellent power on neural prediction, they usually do not provide the uncertainty of the resulting neural representations and derived statistics, such as most exciting inputs (MEIs), from in silico experiments. Here, we present a Bayesian system identification approach to predict neural responses to visual stimuli, and explore whether explicitly modeling network weight variability can be beneficial for identifying neural response properties. To this end, we use variational inference to estimate the posterior distribution of each model weight given the training data. Tests with different neural datasets demonstrate that this method can achieve higher or comparable performance on neural prediction, with a much higher data efficiency compared to Monte Carlo dropout methods and traditional models using point estimates of the model parameters. At the same time, our variational method provides us with an effectively infinite ensemble, avoiding the idiosyncrasy of any single model, to generate MEIs. This allows us to estimate the uncertainty of stimulus-response function, which we have found to be negatively correlated with the predictive performance at model level and may serve to evaluate models. Furthermore, our approach enables us to identify response properties with credible intervals and to determine whether the inferred features are meaningful by performing statistical tests on MEIs. Finally, in silico experiments show that our model generates stimuli driving neuronal activity significantly better than traditional models in the limited-data regime.
Koyuncu, Batuhan; Kıran, Aleyna Dilan; Heilmann, Katja; Hamid, Laith; Buder, Anja; Engert, Veronika; Walter, Martin; Valera, Isabel
From Laboratory to Everyday Life: Personalized Stress Prediction via Smartwatches Proceedings Article
In: ICML'24 Workshop ML for Life and Material Science: From Theory to Industry Applications, 2024.
Abstract | Links | BibTeX | Tags: batu, isabel
@inproceedings{,
title = {From Laboratory to Everyday Life: Personalized Stress Prediction via Smartwatches},
author = {Batuhan Koyuncu and Aleyna Dilan Kıran and Katja Heilmann and Laith Hamid and Anja Buder and Veronika Engert and Martin Walter and Isabel Valera},
url = {https://openreview.net/forum?id=XBtTaeQOWs},
year = {2024},
date = {2024-01-01},
urldate = {2024-01-01},
booktitle = {ICML'24 Workshop ML for Life and Material Science: From Theory to Industry Applications},
abstract = {Accurate prediction of stress in everyday life is essential to prevent chronic stress and maintain health and well-being through early and personalized intervention. With the goal of enabling reliable prediction suitable for everyday life, we present MuStP, a two-stage machine learning pipeline designed to predict stress from low-resolution heart rate (HR) and high-resolution electrocardiography (ECG) measurements from commercial smartwatches. Our model is pre-trained with labeled data collected in a controlled laboratory stress study. Subsequently, we transfer the model for everyday use, enabling it to operate with everyday smartwatch data in various environments. The model transfer strategy effectively addresses the domain shift from laboratory data to highly imbalanced smartwatch data and allows personalization. The empirical results on smartwatch data show that MuStP can predict stress everyday with an F1 score of 0.52, despite the measurements having sparse labels for stress.},
keywords = {batu, isabel},
pubstate = {published},
tppubtype = {inproceedings}
}
Accurate prediction of stress in everyday life is essential to prevent chronic stress and maintain health and well-being through early and personalized intervention. With the goal of enabling reliable prediction suitable for everyday life, we present MuStP, a two-stage machine learning pipeline designed to predict stress from low-resolution heart rate (HR) and high-resolution electrocardiography (ECG) measurements from commercial smartwatches. Our model is pre-trained with labeled data collected in a controlled laboratory stress study. Subsequently, we transfer the model for everyday use, enabling it to operate with everyday smartwatch data in various environments. The model transfer strategy effectively addresses the domain shift from laboratory data to highly imbalanced smartwatch data and allows personalization. The empirical results on smartwatch data show that MuStP can predict stress everyday with an F1 score of 0.52, despite the measurements having sparse labels for stress.
2023
Javaloy, Adrián; Sánchez-Mart'ın, Pablo; Valera, Isabel
Causal normalizing flows: from theory to practice Journal Article Oral
In: CoRR, vol. abs/2306.05415, 2023.
Abstract | Links | BibTeX | Tags: adrian, isabel, oral, pablo
@article{DBLP:journals/corr/abs-2306-05415,
title = {Causal normalizing flows: from theory to practice},
author = {Adrián Javaloy and Pablo Sánchez-Mart'ın and Isabel Valera},
url = {https://doi.org/10.48550/arXiv.2306.05415},
doi = {10.48550/arXiv.2306.05415},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2306.05415},
abstract = {In this work, we deepen on the use of normalizing flows for causal reasoning. Specifically, we first leverage recent results on non-linear ICA to show that causal models are identifiable from observational data given a causal ordering, and thus can be recovered using autoregressive normalizing flows (NFs). Second, we analyze different design and learning choices for causal normalizing flows to capture the underlying causal data-generating process. Third, we describe how to implement the do-operator in causal NFs, and thus, how to answer interventional and counterfactual questions. Finally, in our experiments, we validate our design and training choices through a comprehensive ablation study; compare causal NFs to other approaches for approximating causal models; and empirically demonstrate that causal NFs can be used to address real-world problems—where the presence of mixed discrete-continuous data and partial knowledge on the causal graph is the norm. The code for this work can be found at https://github.com/psanch21/causal-flows.},
keywords = {adrian, isabel, oral, pablo},
pubstate = {published},
tppubtype = {article}
}
In this work, we deepen on the use of normalizing flows for causal reasoning. Specifically, we first leverage recent results on non-linear ICA to show that causal models are identifiable from observational data given a causal ordering, and thus can be recovered using autoregressive normalizing flows (NFs). Second, we analyze different design and learning choices for causal normalizing flows to capture the underlying causal data-generating process. Third, we describe how to implement the do-operator in causal NFs, and thus, how to answer interventional and counterfactual questions. Finally, in our experiments, we validate our design and training choices through a comprehensive ablation study; compare causal NFs to other approaches for approximating causal models; and empirically demonstrate that causal NFs can be used to address real-world problems—where the presence of mixed discrete-continuous data and partial knowledge on the causal graph is the norm. The code for this work can be found at https://github.com/psanch21/causal-flows.
Karimi, Amir-Hossein; Barthe, Gilles; Schölkopf, Bernhard; Valera, Isabel
A Survey of Algorithmic Recourse: Contrastive Explanations and Consequential Recommendations Journal Article
In: ACM Comput. Surv., vol. 55, no. 5, pp. 95:1–95:29, 2023.
Abstract | Links | BibTeX | Tags: amir, isabel
@article{DBLP:journals/csur/KarimiBSV23,
title = {A Survey of Algorithmic Recourse: Contrastive Explanations and Consequential Recommendations},
author = {Amir-Hossein Karimi and Gilles Barthe and Bernhard Schölkopf and Isabel Valera},
url = {https://doi.org/10.1145/3527848},
doi = {10.1145/3527848},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {ACM Comput. Surv.},
volume = {55},
number = {5},
pages = {95:1–95:29},
abstract = {Machine learning is increasingly used to inform decision making in sensitive situations where decisions have consequential effects on individuals’ lives. In these settings, in addition to requiring models to be accurate and robust, socially relevant values such as fairness, privacy, accountability, and explainability play an important role in the adoption and impact of said technologies. In this work, we focus on algorithmic recourse, which is concerned with providing explanations and recommendations to individuals who are unfavorably treated by automated decision-making systems. We first perform an extensive literature review, and align the efforts of many authors by presenting unified definitions, formulations, and solutions to recourse. Then, we provide an overview of the prospective research directions toward which the community may engage, challenging existing assumptions and making explicit connections to other ethical challenges such as security, privacy, and fairness.},
keywords = {amir, isabel},
pubstate = {published},
tppubtype = {article}
}
Machine learning is increasingly used to inform decision making in sensitive situations where decisions have consequential effects on individuals’ lives. In these settings, in addition to requiring models to be accurate and robust, socially relevant values such as fairness, privacy, accountability, and explainability play an important role in the adoption and impact of said technologies. In this work, we focus on algorithmic recourse, which is concerned with providing explanations and recommendations to individuals who are unfavorably treated by automated decision-making systems. We first perform an extensive literature review, and align the efforts of many authors by presenting unified definitions, formulations, and solutions to recourse. Then, we provide an overview of the prospective research directions toward which the community may engage, challenging existing assumptions and making explicit connections to other ethical challenges such as security, privacy, and fairness.
Koyuncu, Batuhan; Sánchez-Mart'ın, Pablo; Peis, Ignacio; Olmos, Pablo M.; Valera, Isabel
Variational Mixture of HyperGenerators for Learning Distributions Over Functions Journal Article
In: CoRR, vol. abs/2302.06223, 2023.
Abstract | Links | BibTeX | Tags: batu, isabel, pablo
@article{DBLP:journals/corr/abs-2302-06223,
title = {Variational Mixture of HyperGenerators for Learning Distributions Over Functions},
author = {Batuhan Koyuncu and Pablo Sánchez-Mart'ın and Ignacio Peis and Pablo M. Olmos and Isabel Valera},
url = {https://doi.org/10.48550/arXiv.2302.06223},
doi = {10.48550/arXiv.2302.06223},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
journal = {CoRR},
volume = {abs/2302.06223},
abstract = {Recent approaches build on implicit neural representations (INRs) to propose generative models over function spaces. However, they are computationally costly when dealing with inference tasks, such as missing data imputation, or directly cannot tackle them. In this work, we propose a novel deep generative model, named VAMoH. VAMoH combines the capabilities of modeling continuous functions using INRs and the inference capabilities of Variational Autoencoders (VAEs). In addition, VAMoH relies on a normalizing flow to define the prior, and a mixture of hypernetworks to parametrize the data log-likelihood. This gives VAMoH a high expressive capability and interpretability. Through experiments on a diverse range of data types, such as images, voxels, and climate data, we show that VAMoH can effectively learn rich distributions over continuous functions. Furthermore, it can perform inference-related tasks, such as conditional super-resolution generation and in-painting, as well or better than previous approaches, while being less computationally demanding.},
keywords = {batu, isabel, pablo},
pubstate = {published},
tppubtype = {article}
}
Recent approaches build on implicit neural representations (INRs) to propose generative models over function spaces. However, they are computationally costly when dealing with inference tasks, such as missing data imputation, or directly cannot tackle them. In this work, we propose a novel deep generative model, named VAMoH. VAMoH combines the capabilities of modeling continuous functions using INRs and the inference capabilities of Variational Autoencoders (VAEs). In addition, VAMoH relies on a normalizing flow to define the prior, and a mixture of hypernetworks to parametrize the data log-likelihood. This gives VAMoH a high expressive capability and interpretability. Through experiments on a diverse range of data types, such as images, voxels, and climate data, we show that VAMoH can effectively learn rich distributions over continuous functions. Furthermore, it can perform inference-related tasks, such as conditional super-resolution generation and in-painting, as well or better than previous approaches, while being less computationally demanding.
Javaloy, Adrián; Sánchez-Mart'ın, Pablo; Levi, Amit; Valera, Isabel
Learnable Graph Convolutional Attention Networks Proceedings Article
In: The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023, OpenReview.net, 2023.
Abstract | Links | BibTeX | Tags: adrian, isabel, pablo
@inproceedings{DBLP:conf/iclr/JavaloySLV23,
title = {Learnable Graph Convolutional Attention Networks},
author = {Adrián Javaloy and Pablo Sánchez-Mart'ın and Amit Levi and Isabel Valera},
url = {https://openreview.net/pdf?id=WsUMeHPo-2},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
booktitle = {The Eleventh International Conference on Learning Representations,
ICLR 2023, Kigali, Rwanda, May 1-5, 2023},
publisher = {OpenReview.net},
abstract = {Existing Graph Neural Networks (GNNs) compute the message exchange between nodes by either aggregating uniformly (convolving) the features of all the neighbor- ing nodes, or by applying a non-uniform score (attending) to the features. Recent works have shown the strengths and weaknesses of the resulting GNN architectures, respectively, GCNs and GATs. In this work, we aim at exploiting the strengths of both approaches to their full extent. To this end, we first introduce the graph convolutional attention layer (CAT), which relies on convolutions to compute the attention scores. Unfortunately, as in the case of GCNs and GATs, we show that there exists no clear winner between the three—neither theoretically nor in practice—as their performance directly depends on the nature of the data (i.e., of the graph and features). This result brings us to the main contribution of our work, the learnable graph convolutional attention network (L-CAT): a GNN architecture that automatically interpolates between GCN, GAT and CAT in each layer, by adding only two scalar parameters. Our results demonstrate that L-CAT is able to efficiently combine different GNN layers along the network, outperforming competing methods in a wide range of datasets, and resulting in a more robust model that reduces the need of cross-validating.},
keywords = {adrian, isabel, pablo},
pubstate = {published},
tppubtype = {inproceedings}
}
Existing Graph Neural Networks (GNNs) compute the message exchange between nodes by either aggregating uniformly (convolving) the features of all the neighbor- ing nodes, or by applying a non-uniform score (attending) to the features. Recent works have shown the strengths and weaknesses of the resulting GNN architectures, respectively, GCNs and GATs. In this work, we aim at exploiting the strengths of both approaches to their full extent. To this end, we first introduce the graph convolutional attention layer (CAT), which relies on convolutions to compute the attention scores. Unfortunately, as in the case of GCNs and GATs, we show that there exists no clear winner between the three—neither theoretically nor in practice—as their performance directly depends on the nature of the data (i.e., of the graph and features). This result brings us to the main contribution of our work, the learnable graph convolutional attention network (L-CAT): a GNN architecture that automatically interpolates between GCN, GAT and CAT in each layer, by adding only two scalar parameters. Our results demonstrate that L-CAT is able to efficiently combine different GNN layers along the network, outperforming competing methods in a wide range of datasets, and resulting in a more robust model that reduces the need of cross-validating.
Langer, Markus; Valera, Isabel
Leveraging Actionable Explanations to Improve People's Reactions to AI-Based Decisions Proceedings Article
In: Steffen, Bernhard (Ed.): Bridging the Gap Between AI and Reality - First International Conference, AISoLA 2023, Crete, Greece, October 23-28, 2023, Selected Papers, pp. 293–306, Springer, 2023.
Abstract | Links | BibTeX | Tags: isabel
@inproceedings{DBLP:conf/vecos/LangerV23,
title = {Leveraging Actionable Explanations to Improve People's Reactions to AI-Based Decisions},
author = {Markus Langer and Isabel Valera},
editor = {Bernhard Steffen},
url = {https://doi.org/10.1007/978-3-031-73741-1_18},
doi = {10.1007/978-3-031-73741-1_18},
year = {2023},
date = {2023-01-01},
urldate = {2023-01-01},
booktitle = {Bridging the Gap Between AI and Reality - First International Conference,
AISoLA 2023, Crete, Greece, October 23-28, 2023, Selected Papers},
volume = {14129},
pages = {293–306},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
abstract = {This paper explores the role of explanations in mitigating negative reactions among people affected by AI-based decisions. While existing research focuses primarily on user perspectives, this study addresses the unique needs of people affected by AI-based decisions. Drawing on justice theory and the algorithmic recourse literature, we propose that actionability is a primary need of people affected by AI-based decisions. Thus, we expected that more actionable explanations – that is, explanations that guide people on how to address negative outcomes – would elicit more favorable reactions than feature relevance explanations or no explanations. In a within-participants experiment, participants (N = 138) imagined being loan applicants and were informed that their loan application had been rejected by AI-based systems at five different banks. Participants received either no explanation, feature relevance explanations, or actionable explanations for this decision. Additionally, we varied the degree of actionability of the features mentioned in the explanations to explore whether features that are more actionable (i.e., reduce the amount of loan) lead to additional positive effects on people’s reactions compared to less actionable features (i.e., increase your income). We found that providing any explanation led to more favorable reactions, and that actionable explanations led to more favorable reactions than feature relevance explanations. However, focusing on the supposedly more actionable feature led to comparably more negative effects possibly due to our specific context of application. We discuss the crucial role that perceived actionability may play for people affected by AI-based decisions as well as the nuanced effects that focusing on different features in explanations may have.},
keywords = {isabel},
pubstate = {published},
tppubtype = {inproceedings}
}
This paper explores the role of explanations in mitigating negative reactions among people affected by AI-based decisions. While existing research focuses primarily on user perspectives, this study addresses the unique needs of people affected by AI-based decisions. Drawing on justice theory and the algorithmic recourse literature, we propose that actionability is a primary need of people affected by AI-based decisions. Thus, we expected that more actionable explanations – that is, explanations that guide people on how to address negative outcomes – would elicit more favorable reactions than feature relevance explanations or no explanations. In a within-participants experiment, participants (N = 138) imagined being loan applicants and were informed that their loan application had been rejected by AI-based systems at five different banks. Participants received either no explanation, feature relevance explanations, or actionable explanations for this decision. Additionally, we varied the degree of actionability of the features mentioned in the explanations to explore whether features that are more actionable (i.e., reduce the amount of loan) lead to additional positive effects on people’s reactions compared to less actionable features (i.e., increase your income). We found that providing any explanation led to more favorable reactions, and that actionable explanations led to more favorable reactions than feature relevance explanations. However, focusing on the supposedly more actionable feature led to comparably more negative effects possibly due to our specific context of application. We discuss the crucial role that perceived actionability may play for people affected by AI-based decisions as well as the nuanced effects that focusing on different features in explanations may have.
2022
Kügelgen, Julius; Karimi, Amir-Hossein; Bhatt, Umang; Valera, Isabel; Weller, Adrian; Schölkopf, Bernhard
On the Fairness of Causal Algorithmic Recourse Proceedings Article
In: Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, Thirty-Fourth Conference on Innovative Applications of Artificial Intelligence, IAAI 2022, The Twelveth Symposium on Educational Advances in Artificial Intelligence, EAAI 2022 Virtual Event, February 22 - March 1, 2022, pp. 9584–9594, AAAI Press, 2022.
Abstract | Links | BibTeX | Tags: amir, isabel, project-fairml
@inproceedings{DBLP:conf/aaai/KugelgenKBVWS22,
title = {On the Fairness of Causal Algorithmic Recourse},
author = {Julius Kügelgen and Amir-Hossein Karimi and Umang Bhatt and Isabel Valera and Adrian Weller and Bernhard Schölkopf},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/21192},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI
2022, Thirty-Fourth Conference on Innovative Applications of Artificial
Intelligence, IAAI 2022, The Twelveth Symposium on Educational Advances
in Artificial Intelligence, EAAI 2022 Virtual Event, February 22
- March 1, 2022},
pages = {9584–9594},
publisher = {AAAI Press},
abstract = {Algorithmic fairness is typically studied from the perspective of predictions. Instead, here we investigate fairness from the perspective of recourse actions suggested to individuals to remedy an unfavourable classification. We propose two new fair-ness criteria at the group and individual level, which—unlike prior work on equalising the average group-wise distance from the decision boundary—explicitly account for causal relationships between features, thereby capturing downstream effects of recourse actions performed in the physical world. We explore how our criteria relate to others, such as counterfactual fairness, and show that fairness of recourse is complementary to fairness of prediction. We study theoretically and empirically how to enforce fair causal recourse by altering the classifier and perform a case study on the Adult dataset. Finally, we discuss whether fairness violations in the data generating process revealed by our criteria may be better addressed by societal interventions as opposed to constraints on the classifier.},
keywords = {amir, isabel, project-fairml},
pubstate = {published},
tppubtype = {inproceedings}
}
Algorithmic fairness is typically studied from the perspective of predictions. Instead, here we investigate fairness from the perspective of recourse actions suggested to individuals to remedy an unfavourable classification. We propose two new fair-ness criteria at the group and individual level, which—unlike prior work on equalising the average group-wise distance from the decision boundary—explicitly account for causal relationships between features, thereby capturing downstream effects of recourse actions performed in the physical world. We explore how our criteria relate to others, such as counterfactual fairness, and show that fairness of recourse is complementary to fairness of prediction. We study theoretically and empirically how to enforce fair causal recourse by altering the classifier and perform a case study on the Adult dataset. Finally, we discuss whether fairness violations in the data generating process revealed by our criteria may be better addressed by societal interventions as opposed to constraints on the classifier.
Javaloy, Adrián; Valera, Isabel
RotoGrad: Gradient Homogenization in Multitask Learning Proceedings Article Spotlight
In: The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022, OpenReview.net, 2022.
Abstract | Links | BibTeX | Tags: adrian, isabel, spotlight
@inproceedings{DBLP:conf/iclr/JavaloyV22,
title = {RotoGrad: Gradient Homogenization in Multitask Learning},
author = {Adrián Javaloy and Isabel Valera},
url = {https://openreview.net/forum?id=T8wHz4rnuGL},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {The Tenth International Conference on Learning Representations, ICLR
2022, Virtual Event, April 25-29, 2022},
publisher = {OpenReview.net},
abstract = {Multitask learning is being increasingly adopted in applications domains like computer vision and reinforcement learning. However, optimally exploiting its advantages remains a major challenge due to the effect of negative transfer. Previous works have tracked down this issue to the disparities in gradient magnitudes and directions across tasks, when optimizing the shared network parameters. While recent work has acknowledged that negative transfer is a two-fold problem, existing approaches fall short as they only focus on either homogenizing the gradient magnitude across tasks; or greedily change the gradient directions, overlooking future conflicts. In this work, we introduce RotoGrad, an algorithm that tackles negative transfer as a whole: it jointly homogenizes gradient magnitudes and directions, while ensuring training convergence. We show that RotoGrad outperforms competing methods in complex problems, including multi-label classification in CelebA and computer vision tasks in the NYUv2 dataset. A Pytorch implementation can be found in https://github.com/adrianjav/rotograd.},
keywords = {adrian, isabel, spotlight},
pubstate = {published},
tppubtype = {inproceedings}
}
Multitask learning is being increasingly adopted in applications domains like computer vision and reinforcement learning. However, optimally exploiting its advantages remains a major challenge due to the effect of negative transfer. Previous works have tracked down this issue to the disparities in gradient magnitudes and directions across tasks, when optimizing the shared network parameters. While recent work has acknowledged that negative transfer is a two-fold problem, existing approaches fall short as they only focus on either homogenizing the gradient magnitude across tasks; or greedily change the gradient directions, overlooking future conflicts. In this work, we introduce RotoGrad, an algorithm that tackles negative transfer as a whole: it jointly homogenizes gradient magnitudes and directions, while ensuring training convergence. We show that RotoGrad outperforms competing methods in complex problems, including multi-label classification in CelebA and computer vision tasks in the NYUv2 dataset. A Pytorch implementation can be found in https://github.com/adrianjav/rotograd.
Camps-Valls, Gustau; Ruiz, Francisco J. R.; Valera, Isabel (Ed.)
PMLR, vol. 151, 2022.
@proceedings{DBLP:conf/aistats/2022,
title = {International Conference on Artificial Intelligence and Statistics,
AISTATS 2022, 28-30 March 2022, Virtual Event},
editor = {Gustau Camps-Valls and Francisco J. R. Ruiz and Isabel Valera},
url = {http://proceedings.mlr.press/v151/},
year = {2022},
date = {2022-01-01},
volume = {151},
publisher = {PMLR},
series = {Proceedings of Machine Learning Research},
keywords = {isabel},
pubstate = {published},
tppubtype = {proceedings}
}
Javaloy, Adrián; Meghdadi, Maryam; Valera, Isabel
Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization Journal Article Spotlight
In: CoRR, vol. abs/2206.04496, 2022.
Abstract | Links | BibTeX | Tags: adrian, isabel, maryam, project-robustgenerative, spotlight, variational autoencoder
@article{DBLP:journals/corr/abs-2206-04496,
title = {Mitigating Modality Collapse in Multimodal VAEs via Impartial Optimization},
author = {Adrián Javaloy and Maryam Meghdadi and Isabel Valera},
url = {https://doi.org/10.48550/arXiv.2206.04496},
doi = {10.48550/arXiv.2206.04496},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
journal = {CoRR},
volume = {abs/2206.04496},
abstract = {A number of variational autoencoders (VAEs) have recently emerged with the aim of modeling multimodal data, e.g., to jointly model images and their corresponding captions. Still, multimodal VAEs tend to focus solely on a subset of the modalities, e.g., by fitting the image while neglecting the caption. We refer to this limitation as modality collapse. In this work, we argue that this effect is a consequence of conflicting gradients during multimodal VAE training. We show how to detect the sub-graphs in the computational graphs where gradients conflict (impartiality blocks), as well as how to leverage existing gradient-conflict solutions from multitask learning to mitigate modality collapse. That is, to ensure impartial optimization across modalities. We apply our training framework to several multimodal VAE models, losses and datasets from the literature, and empirically show that our framework significantly improves the reconstruction performance, conditional generation, and coherence of the latent space across modalities.},
keywords = {adrian, isabel, maryam, project-robustgenerative, spotlight, variational autoencoder},
pubstate = {published},
tppubtype = {article}
}
A number of variational autoencoders (VAEs) have recently emerged with the aim of modeling multimodal data, e.g., to jointly model images and their corresponding captions. Still, multimodal VAEs tend to focus solely on a subset of the modalities, e.g., by fitting the image while neglecting the caption. We refer to this limitation as modality collapse. In this work, we argue that this effect is a consequence of conflicting gradients during multimodal VAE training. We show how to detect the sub-graphs in the computational graphs where gradients conflict (impartiality blocks), as well as how to leverage existing gradient-conflict solutions from multitask learning to mitigate modality collapse. That is, to ensure impartial optimization across modalities. We apply our training framework to several multimodal VAE models, losses and datasets from the literature, and empirically show that our framework significantly improves the reconstruction performance, conditional generation, and coherence of the latent space across modalities.
Sánchez-Mart'ın, Pablo; Rateike, Miriam; Valera, Isabel
VACA: Designing Variational Graph Autoencoders for Causal Queries Proceedings Article
In: Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI 2022, Thirty-Fourth Conference on Innovative Applications of Artificial Intelligence, IAAI 2022, The Twelveth Symposium on Educational Advances in Artificial Intelligence, EAAI 2022 Virtual Event, February 22 - March 1, 2022, pp. 8159–8168, AAAI Press, 2022.
Abstract | Links | BibTeX | Tags: isabel, miriam, pablo
@inproceedings{DBLP:conf/aaai/Sanchez-MartinR22b,
title = {VACA: Designing Variational Graph Autoencoders for Causal Queries},
author = {Pablo Sánchez-Mart'ın and Miriam Rateike and Isabel Valera},
url = {https://ojs.aaai.org/index.php/AAAI/article/view/20789},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {Thirty-Sixth AAAI Conference on Artificial Intelligence, AAAI
2022, Thirty-Fourth Conference on Innovative Applications of Artificial
Intelligence, IAAI 2022, The Twelveth Symposium on Educational Advances
in Artificial Intelligence, EAAI 2022 Virtual Event, February 22
- March 1, 2022},
pages = {8159–8168},
publisher = {AAAI Press},
abstract = {In this paper, we introduce VACA, a novel class of variational graph autoencoders for causal inference in the absence of hidden confounders, when only observational data and the causal graph are available. Without making any parametric assumptions, VACA mimics the necessary properties of a Structural Causal Model (SCM) to provide a flexible and practical framework for approximating interventions (do-operator) and abduction-action-prediction steps. As a result, and as shown by our empirical results, VACA accurately approximates the interventional and counterfactual distributions on diverse SCMs. Finally, we apply VACA to evaluate counterfactual fairness in fair classification problems, as well as to learn fair classifiers without compromising performance.},
keywords = {isabel, miriam, pablo},
pubstate = {published},
tppubtype = {inproceedings}
}
In this paper, we introduce VACA, a novel class of variational graph autoencoders for causal inference in the absence of hidden confounders, when only observational data and the causal graph are available. Without making any parametric assumptions, VACA mimics the necessary properties of a Structural Causal Model (SCM) to provide a flexible and practical framework for approximating interventions (do-operator) and abduction-action-prediction steps. As a result, and as shown by our empirical results, VACA accurately approximates the interventional and counterfactual distributions on diverse SCMs. Finally, we apply VACA to evaluate counterfactual fairness in fair classification problems, as well as to learn fair classifiers without compromising performance.
Rateike, Miriam; Majumdar, Ayan; Mineeva, Olga; Gummadi, Krishna P.; Valera, Isabel
Don't Throw it Away! The Utility of Unlabeled Data in Fair Decision Making Proceedings Article
In: FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency, Seoul, Republic of Korea, June 21 - 24, 2022, pp. 1421–1433, ACM, 2022.
Abstract | Links | BibTeX | Tags: ayanm, decision making, fair representation, fairness, isabel, label bias, miriam, project-fairml, selection bias, variational autoencoder
@inproceedings{DBLP:conf/fat/RateikeMMGV22,
title = {Don't Throw it Away! The Utility of Unlabeled Data in Fair Decision Making},
author = {Miriam Rateike and Ayan Majumdar and Olga Mineeva and Krishna P. Gummadi and Isabel Valera},
url = {https://doi.org/10.1145/3531146.3533199},
doi = {10.1145/3531146.3533199},
year = {2022},
date = {2022-01-01},
urldate = {2022-01-01},
booktitle = {FAccT '22: 2022 ACM Conference on Fairness, Accountability, and
Transparency, Seoul, Republic of Korea, June 21 - 24, 2022},
pages = {1421–1433},
publisher = {ACM},
abstract = {unbiased, i.e., equally distributed across socially salient groups. In many practical settings, the ground-truth cannot be directly observed, and instead, we have to rely on a biased proxy measure of the ground-truth, i.e., biased labels, in the data. In addition, data is often selectively labeled, i.e., even the biased labels are only observed for a small fraction of the data that received a positive decision. To overcome label and selection biases, recent work proposes to learn stochastic, exploring decision policies via i) online training of new policies at each time-step and ii) enforcing fairness as a constraint on performance. However, the existing approach uses only labeled data, disregarding a large amount of unlabeled data, and thereby suffers from high instability and variance in the learned decision policies at different times. In this paper, we propose a novel method based on a variational autoencoder for practical fair decision-making. Our method learns an unbiased data representation leveraging both labeled and unlabeled data and uses the representations to learn a policy in an online process. Using synthetic data, we empirically validate that our method converges to the optimal (fair) policy according to the ground-truth with low variance. In real-world experiments, we further show that our training approach not only offers a more stable learning process but also yields policies with higher fairness as well as utility than previous approaches.},
keywords = {ayanm, decision making, fair representation, fairness, isabel, label bias, miriam, project-fairml, selection bias, variational autoencoder},
pubstate = {published},
tppubtype = {inproceedings}
}
unbiased, i.e., equally distributed across socially salient groups. In many practical settings, the ground-truth cannot be directly observed, and instead, we have to rely on a biased proxy measure of the ground-truth, i.e., biased labels, in the data. In addition, data is often selectively labeled, i.e., even the biased labels are only observed for a small fraction of the data that received a positive decision. To overcome label and selection biases, recent work proposes to learn stochastic, exploring decision policies via i) online training of new policies at each time-step and ii) enforcing fairness as a constraint on performance. However, the existing approach uses only labeled data, disregarding a large amount of unlabeled data, and thereby suffers from high instability and variance in the learned decision policies at different times. In this paper, we propose a novel method based on a variational autoencoder for practical fair decision-making. Our method learns an unbiased data representation leveraging both labeled and unlabeled data and uses the representations to learn a policy in an online process. Using synthetic data, we empirically validate that our method converges to the optimal (fair) policy according to the ground-truth with low variance. In real-world experiments, we further show that our training approach not only offers a more stable learning process but also yields policies with higher fairness as well as utility than previous approaches.
2021
Javaloy, Adrián; Meghdadi, Maryam; Valera, Isabel
Boosting heterogeneous VAEs via multi-objective optimization Workshop
2021.
Abstract | Links | BibTeX | Tags: adrian, isabel, maryam, project-robustgenerative
@workshop{nokey,
title = {Boosting heterogeneous VAEs via multi-objective optimization},
author = {Adrián Javaloy and Maryam Meghdadi and Isabel Valera},
url = {http://adrian.javaloy.com/publication/mo-vae/},
year = {2021},
date = {2021-12-01},
urldate = {2021-12-01},
abstract = {A number of variational autoencoders (VAEs) have recently emerged with the aim of modeling multimodal data, e.g., to jointly model images and their corresponding captions. Still, multimodal VAEs tend to focus solely on a subset of the modalities, e.g., by fitting the image while neglecting the caption. We refer to this limitation as modality collapse. In this work, we argue that this effect is a consequence of conflicting gradients during multimodal VAE training. We show how to detect the sub-graphs in the computational graphs where gradients conflict (impartiality blocks), as well as how to leverage existing gradient-conflict solutions from multitask learning to mitigate modality collapse. That is, to ensure impartial optimization across modalities. We apply our training framework to several multimodal VAE models, losses and datasets from the literature, and empirically show that our framework significantly improves the reconstruction performance, conditional generation, and coherence of the latent space across modalities.},
keywords = {adrian, isabel, maryam, project-robustgenerative},
pubstate = {published},
tppubtype = {workshop}
}
A number of variational autoencoders (VAEs) have recently emerged with the aim of modeling multimodal data, e.g., to jointly model images and their corresponding captions. Still, multimodal VAEs tend to focus solely on a subset of the modalities, e.g., by fitting the image while neglecting the caption. We refer to this limitation as modality collapse. In this work, we argue that this effect is a consequence of conflicting gradients during multimodal VAE training. We show how to detect the sub-graphs in the computational graphs where gradients conflict (impartiality blocks), as well as how to leverage existing gradient-conflict solutions from multitask learning to mitigate modality collapse. That is, to ensure impartial optimization across modalities. We apply our training framework to several multimodal VAE models, losses and datasets from the literature, and empirically show that our framework significantly improves the reconstruction performance, conditional generation, and coherence of the latent space across modalities.
Mohammadi, Kiarash; Karimi, Amir-Hossein; Barthe, Gilles; Valera, Isabel
Scaling Guarantees for Nearest Counterfactual Explanations Proceedings Article
In: Fourcade, Marion; Kuipers, Benjamin; Lazar, Seth; Mulligan, Deirdre K. (Ed.): AIES '21: AAAI/ACM Conference on AI, Ethics, and Society, Virtual Event, USA, May 19-21, 2021, pp. 177–187, ACM, 2021.
Abstract | Links | BibTeX | Tags: amir, isabel, project-interpretableML
@inproceedings{DBLP:conf/aies/MohammadiKBV21,
title = {Scaling Guarantees for Nearest Counterfactual Explanations},
author = {Kiarash Mohammadi and Amir-Hossein Karimi and Gilles Barthe and Isabel Valera},
editor = {Marion Fourcade and Benjamin Kuipers and Seth Lazar and Deirdre K. Mulligan},
url = {https://doi.org/10.1145/3461702.3462514},
doi = {10.1145/3461702.3462514},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {AIES '21: AAAI/ACM Conference on AI, Ethics, and Society, Virtual
Event, USA, May 19-21, 2021},
pages = {177--187},
publisher = {ACM},
abstract = {Counterfactual explanations (CFE) are being widely used to explain algorithmic decisions, especially in consequential decision-making contexts (e.g., loan approval or pretrial bail). In this context, CFEs aim to provide individuals affected by an algorithmic decision with the most similar individual (i.e., nearest individual) with a different outcome. However, while an increasing number of works propose algorithms to compute CFEs, such approaches either lack in optimality of distance (i.e., they do not return the nearest individual) and perfect coverage (i.e., they do not provide a CFE for all individuals); or they do not scale to complex models such as neural networks. In this work, we provide a framework based on Mixed-Integer Programming (MIP) to compute nearest counterfactual explanations for the outcomes of neural networks, with both provable guarantees and runtimes comparable to gradient-based approaches. Our experiments on the Adult, COMPAS, and Credit datasets show that, in contrast with previous methods, our approach allows for efficiently computing diverse CFEs with both distance guarantees and perfect coverage.},
keywords = {amir, isabel, project-interpretableML},
pubstate = {published},
tppubtype = {inproceedings}
}
Counterfactual explanations (CFE) are being widely used to explain algorithmic decisions, especially in consequential decision-making contexts (e.g., loan approval or pretrial bail). In this context, CFEs aim to provide individuals affected by an algorithmic decision with the most similar individual (i.e., nearest individual) with a different outcome. However, while an increasing number of works propose algorithms to compute CFEs, such approaches either lack in optimality of distance (i.e., they do not return the nearest individual) and perfect coverage (i.e., they do not provide a CFE for all individuals); or they do not scale to complex models such as neural networks. In this work, we provide a framework based on Mixed-Integer Programming (MIP) to compute nearest counterfactual explanations for the outcomes of neural networks, with both provable guarantees and runtimes comparable to gradient-based approaches. Our experiments on the Adult, COMPAS, and Credit datasets show that, in contrast with previous methods, our approach allows for efficiently computing diverse CFEs with both distance guarantees and perfect coverage.
Karimi, Amir-Hossein; Schölkopf, Bernhard; Valera, Isabel
Algorithmic Recourse: from Counterfactual Explanations to Interventions Proceedings Article
In: Elish, Madeleine Clare; Isaac, William; Zemel, Richard S. (Ed.): FAccT '21: 2021 ACM Conference on Fairness, Accountability, and Transparency, Virtual Event / Toronto, Canada, March 3-10, 2021, pp. 353–362, ACM, 2021.
Abstract | Links | BibTeX | Tags: amir, isabel, project-interpretableML
@inproceedings{DBLP:conf/fat/KarimiSV21,
title = {Algorithmic Recourse: from Counterfactual Explanations to Interventions},
author = {Amir-Hossein Karimi and Bernhard Schölkopf and Isabel Valera},
editor = {Madeleine Clare Elish and William Isaac and Richard S. Zemel},
url = {https://doi.org/10.1145/3442188.3445899},
doi = {10.1145/3442188.3445899},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {FAccT '21: 2021 ACM Conference on Fairness, Accountability, and
Transparency, Virtual Event / Toronto, Canada, March 3-10, 2021},
pages = {353--362},
publisher = {ACM},
abstract = {As machine learning is increasingly used to inform consequential decision-making (e.g., pre-trial bail and loan approval), it becomes important to explain how the system arrived at its decision, and also suggest actions to achieve a favorable decision. Counterfactual explanations -"how the world would have (had) to be different for a desirable outcome to occur"- aim to satisfy these criteria. Existing works have primarily focused on designing algorithms to obtain counterfactual explanations for a wide range of settings. However, it has largely been overlooked that ultimately, one of the main objectives is to allow people to act rather than just understand. In layman's terms, counterfactual explanations inform an individual where they need to get to, but not how to get there. In this work, we rely on causal reasoning to caution against the use of counterfactual explanations as a recommendable set of actions for recourse. Instead, we propose a shift of paradigm from recourse via nearest counterfactual explanations to recourse through minimal interventions, shifting the focus from explanations to interventions.},
keywords = {amir, isabel, project-interpretableML},
pubstate = {published},
tppubtype = {inproceedings}
}
As machine learning is increasingly used to inform consequential decision-making (e.g., pre-trial bail and loan approval), it becomes important to explain how the system arrived at its decision, and also suggest actions to achieve a favorable decision. Counterfactual explanations -"how the world would have (had) to be different for a desirable outcome to occur"- aim to satisfy these criteria. Existing works have primarily focused on designing algorithms to obtain counterfactual explanations for a wide range of settings. However, it has largely been overlooked that ultimately, one of the main objectives is to allow people to act rather than just understand. In layman's terms, counterfactual explanations inform an individual where they need to get to, but not how to get there. In this work, we rely on causal reasoning to caution against the use of counterfactual explanations as a recommendable set of actions for recourse. Instead, we propose a shift of paradigm from recourse via nearest counterfactual explanations to recourse through minimal interventions, shifting the focus from explanations to interventions.
Schöffer, Jakob; Kuehl, Niklas; Valera, Isabel
A Ranking Approach to Fair Classification Proceedings Article
In: COMPASS '21: ACM SIGCAS Conference on Computing and Sustainable Societies, Virtual Event, Australia, 28 June 2021 - 2 July 2021, pp. 115–125, ACM, 2021.
Abstract | Links | BibTeX | Tags: isabel, project-fairml
@inproceedings{DBLP:conf/dev/SchofferKV21,
title = {A Ranking Approach to Fair Classification},
author = {Jakob Schöffer and Niklas Kuehl and Isabel Valera},
url = {https://doi.org/10.1145/3460112.3471950},
doi = {10.1145/3460112.3471950},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
booktitle = {COMPASS '21: ACM SIGCAS Conference on Computing and Sustainable
Societies, Virtual Event, Australia, 28 June 2021 - 2 July 2021},
pages = {115--125},
publisher = {ACM},
abstract = {Algorithmic decision systems are increasingly used in areas such as hiring, school admission, or loan approval. Typically, these systems rely on labeled data for training a classification model. However, in many scenarios, ground-truth labels are unavailable, and instead we have only access to imperfect labels as the result of (potentially biased) human-made decisions. Despite being imperfect, historical decisions often contain some useful information on the unobserved true labels. In this paper, we focus on scenarios where only imperfect labels are available and propose a new fair ranking-based decision system based on monotonic relationships between legitimate features and the outcome. Our approach is both intuitive and easy to implement, and thus particularly suitable for adoption in real-world settings. More in detail, we introduce a distance-based decision criterion, which incorporates useful information from historical decisions and accounts for unwanted correlation between protected and legitimate features. Through extensive experiments on synthetic and real-world data, we show that our method is fair in the sense that a) it assigns the desirable outcome to the most qualified individuals, and b) it removes the effect of stereotypes in decision-making, thereby outperforming traditional classification algorithms. Additionally, we are able to show theoretically that our method is consistent with a prominent concept of individual fairness which states that “similar individuals should be treated similarly.”},
keywords = {isabel, project-fairml},
pubstate = {published},
tppubtype = {inproceedings}
}
Algorithmic decision systems are increasingly used in areas such as hiring, school admission, or loan approval. Typically, these systems rely on labeled data for training a classification model. However, in many scenarios, ground-truth labels are unavailable, and instead we have only access to imperfect labels as the result of (potentially biased) human-made decisions. Despite being imperfect, historical decisions often contain some useful information on the unobserved true labels. In this paper, we focus on scenarios where only imperfect labels are available and propose a new fair ranking-based decision system based on monotonic relationships between legitimate features and the outcome. Our approach is both intuitive and easy to implement, and thus particularly suitable for adoption in real-world settings. More in detail, we introduce a distance-based decision criterion, which incorporates useful information from historical decisions and accounts for unwanted correlation between protected and legitimate features. Through extensive experiments on synthetic and real-world data, we show that our method is fair in the sense that a) it assigns the desirable outcome to the most qualified individuals, and b) it removes the effect of stereotypes in decision-making, thereby outperforming traditional classification algorithms. Additionally, we are able to show theoretically that our method is consistent with a prominent concept of individual fairness which states that “similar individuals should be treated similarly.”
Hutter, Frank; Kersting, Kristian; Lijffijt, Jefrey; Valera, Isabel (Ed.)
Springer, vol. 12457, 2021, ISBN: 978-3-030-67657-5.
Abstract | Links | BibTeX | Tags: isabel
@proceedings{DBLP:conf/pkdd/2020-1,
title = {Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2020, Ghent, Belgium, September 14-18, 2020, Proceedings, Part I},
editor = {Frank Hutter and Kristian Kersting and Jefrey Lijffijt and Isabel Valera},
url = {https://doi.org/10.1007/978-3-030-67658-2},
doi = {10.1007/978-3-030-67658-2},
isbn = {978-3-030-67657-5},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
volume = {12457},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
abstract = {Pattern Mining; clustering; privacy and fairness; (social) network analysis and computational social science; dimensionality reduction and autoencoders; domain adaptation; sketching, sampling, and binary projections; graphical models and causality; (spatio-) temporal data and recurrent neural networks; collaborative filtering and matrix completion.},
keywords = {isabel},
pubstate = {published},
tppubtype = {proceedings}
}
Pattern Mining; clustering; privacy and fairness; (social) network analysis and computational social science; dimensionality reduction and autoencoders; domain adaptation; sketching, sampling, and binary projections; graphical models and causality; (spatio-) temporal data and recurrent neural networks; collaborative filtering and matrix completion.
Hutter, Frank; Kersting, Kristian; Lijffijt, Jefrey; Valera, Isabel (Ed.)
Springer, vol. 12458, 2021, ISBN: 978-3-030-67660-5.
Abstract | Links | BibTeX | Tags: isabel
@proceedings{DBLP:conf/pkdd/2020-2,
title = {Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2020, Ghent, Belgium, September 14-18, 2020, Proceedings, Part II},
editor = {Frank Hutter and Kristian Kersting and Jefrey Lijffijt and Isabel Valera},
url = {https://doi.org/10.1007/978-3-030-67661-2},
doi = {10.1007/978-3-030-67661-2},
isbn = {978-3-030-67660-5},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
volume = {12458},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
abstract = {Deep learning optimization and theory;active learning; adversarial learning; federated learning; Kernel methods and online learning; partial label learning; reinforcement learning; transfer and multi-task learning; Bayesian optimization and few-shot learning.},
keywords = {isabel},
pubstate = {published},
tppubtype = {proceedings}
}
Deep learning optimization and theory;active learning; adversarial learning; federated learning; Kernel methods and online learning; partial label learning; reinforcement learning; transfer and multi-task learning; Bayesian optimization and few-shot learning.
Hutter, Frank; Kersting, Kristian; Lijffijt, Jefrey; Valera, Isabel (Ed.)
Springer, vol. 12459, 2021, ISBN: 978-3-030-67663-6.
Abstract | Links | BibTeX | Tags: isabel
@proceedings{DBLP:conf/pkdd/2020-3,
title = {Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2020, Ghent, Belgium, September 14-18, 2020, Proceedings, Part III},
editor = {Frank Hutter and Kristian Kersting and Jefrey Lijffijt and Isabel Valera},
url = {https://doi.org/10.1007/978-3-030-67664-3},
doi = {10.1007/978-3-030-67664-3},
isbn = {978-3-030-67663-6},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
volume = {12459},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
abstract = {Combinatorial optimization; large-scale optimization and differential privacy; boosting and ensemble methods; Bayesian methods; architecture of neural networks; graph neural networks; Gaussian processes; computer vision and image processing; natural language processing; bioinformatics.},
keywords = {isabel},
pubstate = {published},
tppubtype = {proceedings}
}
Combinatorial optimization; large-scale optimization and differential privacy; boosting and ensemble methods; Bayesian methods; architecture of neural networks; graph neural networks; Gaussian processes; computer vision and image processing; natural language processing; bioinformatics.
Sánchez-Mart'ın, Pablo; Rateike, Miriam; Valera, Isabel
VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queries Journal Article
In: CoRR, vol. abs/2110.14690, 2021.
Abstract | Links | BibTeX | Tags: isabel
@article{DBLP:journals/corr/abs-2110-14690,
title = {VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queries},
author = {Pablo Sánchez-Mart'ın and Miriam Rateike and Isabel Valera},
url = {https://arxiv.org/abs/2110.14690},
year = {2021},
date = {2021-01-01},
urldate = {2021-01-01},
journal = {CoRR},
volume = {abs/2110.14690},
abstract = {In this paper, we introduce VACA, a novel class of variational graph autoencoders for causal inference in the absence of hidden confounders, when only observational data and the causal graph are available. Without making any parametric assumptions, VACA mimics the necessary properties of a Structural Causal Model (SCM) to provide a flexible and practical framework for approximating interventions (do-operator) and abduction-action-prediction steps. As a result, and as shown by our empirical results, VACA accurately approximates the interventional and counterfactual distributions on diverse SCMs. Finally, we apply VACA to evaluate counterfactual fairness in fair classification problems, as well as to learn fair classifiers without compromising performance.},
keywords = {isabel},
pubstate = {published},
tppubtype = {article}
}
In this paper, we introduce VACA, a novel class of variational graph autoencoders for causal inference in the absence of hidden confounders, when only observational data and the causal graph are available. Without making any parametric assumptions, VACA mimics the necessary properties of a Structural Causal Model (SCM) to provide a flexible and practical framework for approximating interventions (do-operator) and abduction-action-prediction steps. As a result, and as shown by our empirical results, VACA accurately approximates the interventional and counterfactual distributions on diverse SCMs. Finally, we apply VACA to evaluate counterfactual fairness in fair classification problems, as well as to learn fair classifiers without compromising performance.
2020
Javaloy, Adrián; Valera, Isabel
Lipschitz standardization for robust multivariate learning Journal Article
In: CoRR, vol. abs/2002.11369, 2020.
Abstract | Links | BibTeX | Tags: adrian, isabel
@article{DBLP:journals/corr/abs-2002-11369,
title = {Lipschitz standardization for robust multivariate learning},
author = {Adrián Javaloy and Isabel Valera},
url = {https://arxiv.org/abs/2002.11369},
year = {2020},
date = {2020-01-01},
urldate = {2020-01-01},
journal = {CoRR},
volume = {abs/2002.11369},
abstract = {Probabilistic learning is increasingly being tackled as an optimization problem, with gradient-based approaches as predominant methods. When modelling multivariate likelihoods, a usual but undesirable outcome is that the learned model fits only a subset of the observed variables, overlooking the rest. In this work, we study this problem through the lens of multitask learning (MTL), where similar effects have been broadly studied. While MTL solutions do not directly apply in the probabilistic setting (as they cannot handle the likelihood constraints) we show that similar ideas may be leveraged during data preprocessing. First, we show that data standardization often helps under common continuous likelihoods, but it is not enough in the general case, specially under mixed continuous and discrete likelihood models. In order for balance multivariate learning, we then propose a novel data preprocessing, Lipschitz standardization, which balances the local Lipschitz smoothness across variables. Our experiments on real-world datasets show that Lipschitz standardization leads to more accurate multivariate models than the ones learned using existing data preprocessing techniques. The models and datasets employed in the experiments can be found in this URL https://github.com/adrianjav/lipschitz-standardization},
keywords = {adrian, isabel},
pubstate = {published},
tppubtype = {article}
}
Probabilistic learning is increasingly being tackled as an optimization problem, with gradient-based approaches as predominant methods. When modelling multivariate likelihoods, a usual but undesirable outcome is that the learned model fits only a subset of the observed variables, overlooking the rest. In this work, we study this problem through the lens of multitask learning (MTL), where similar effects have been broadly studied. While MTL solutions do not directly apply in the probabilistic setting (as they cannot handle the likelihood constraints) we show that similar ideas may be leveraged during data preprocessing. First, we show that data standardization often helps under common continuous likelihoods, but it is not enough in the general case, specially under mixed continuous and discrete likelihood models. In order for balance multivariate learning, we then propose a novel data preprocessing, Lipschitz standardization, which balances the local Lipschitz smoothness across variables. Our experiments on real-world datasets show that Lipschitz standardization leads to more accurate multivariate models than the ones learned using existing data preprocessing techniques. The models and datasets employed in the experiments can be found in this URL https://github.com/adrianjav/lipschitz-standardization
Project Contributors
- Batuhan Koyuncu
- Deborah Kanubala
- Georgi Vitanov
- Huyen Thuc Khanh Vo
- Isabel Valera
- Kavya Gupta
- Lena Marie Budde
- María Martínez García