Fair ML
Our research group has been a pioneer in in laying the methodological foundations for fairness in ML, and in particular in providing algorithmic solutions to the limitations of common practices in this research area, which are often associated with high social costs in terms of unfairness.
Our main contributions to fair ML include: i) new fairness definitions (NeurIPS’17; WWW’17, best paper award honorable mention); ii) flexible learning frameworks for the design of fair classifiers (AISTATS’17; JMLR’19; AAAI’19); and iii) ML algorithms to enhance fairness and accuracy of human decision-makers (NeurIPS’18). More recently, we have highlighted the limitations of previous work on algorithmic fairness and propose a methodological paradigm shift from fairness predictions to fair decisions.
First, we have shown that learning to decide rather than to predict is necessary to ensure algorithmic fairness under realistic assumptions about the data collection process (AISTATS’20, FaccT’22). Second, we have conducted research at the intersection of algorithmic fairness and causality to: i) propose a novel causal notion of fairness that complements fairness in predictions by accounting for the effort required for individuals to recover from an unfavorable decision (‘Fairness of Causal Algorithmic Recourse’; AAAI 2022); ii) audit and enforce any causal notion of fairness under realistic assumptions in algorithmic decision making (‘VACA’; AAAI 2022).
Our ongoing research in this field, aims to further progress in the context of fairness in algorithmic decision making by i) developing ML approaches to algorithmic decision making that operate under realistic assumptions about the data collection process, while at the same time ii) ensuring that the outcomes do not wrongfully impose a relative disadvantage to individuals based on their assignment to a socio-demographic group.
References
2022
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.
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.
2021
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.
2020
Fair Decisions Despite Imperfect Predictions Proceedings Article
In: Chiappa, Silvia; Calandra, Roberto (Ed.): The 23rd International Conference on Artificial Intelligence and Statistics,
AISTATS 2020, 26-28 August 2020, Online [Palermo, Sicily, Italy], pp. 277–287, PMLR, 2020.
2019
Fairness Constraints: A Flexible Approach for Fair Classification Journal Article
In: J. Mach. Learn. Res., vol. 20, pp. 75:1–75:42, 2019.
One-Network Adversarial Fairness Proceedings Article
In: The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI
2019, The Thirty-First Innovative Applications of Artificial Intelligence
Conference, IAAI 2019, The Ninth AAAI Symposium on Educational
Advances in Artificial Intelligence, EAAI 2019, Honolulu, Hawaii,
USA, January 27 - February 1, 2019, pp. 2412–2420, AAAI Press, 2019.
2018
Enhancing the Accuracy and Fairness of Human Decision Making Proceedings Article
In: Bengio, Samy; Wallach, Hanna M.; Larochelle, Hugo; Grauman, Kristen; Cesa-Bianchi, Nicolò; Garnett, Roman (Ed.): Advances in Neural Information Processing Systems 31: Annual Conference
on Neural Information Processing Systems 2018, NeurIPS 2018, December
3-8, 2018, Montréal, Canada, pp. 1774–1783, 2018.
2017
Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment Proceedings Article
In: Barrett, Rick; Cummings, Rick; Agichtein, Eugene; Gabrilovich, Evgeniy (Ed.): Proceedings of the 26th International Conference on World Wide Web,
WWW 2017, Perth, Australia, April 3-7, 2017, pp. 1171–1180, ACM, 2017.
Fairness Constraints: Mechanisms for Fair Classification Proceedings Article
In: Singh, Aarti; Zhu, Xiaojin (Jerry) (Ed.): Proceedings of the 20th International Conference on Artificial Intelligence
and Statistics, AISTATS 2017, 20-22 April 2017, Fort Lauderdale,
FL, USA, pp. 962–970, PMLR, 2017.
From Parity to Preference-based Notions of Fairness in Classification Proceedings Article
In: Guyon, Isabelle; Luxburg, Ulrike; Bengio, Samy; Wallach, Hanna M.; Fergus, Rob; Vishwanathan, S. V. N.; Garnett, Roman (Ed.): Advances in Neural Information Processing Systems 30: Annual Conference
on Neural Information Processing Systems 2017, December 4-9, 2017,
Long Beach, CA, USA, pp. 229–239, 2017.
2022
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.
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.
2021
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.
2020
Fair Decisions Despite Imperfect Predictions Proceedings Article
In: Chiappa, Silvia; Calandra, Roberto (Ed.): The 23rd International Conference on Artificial Intelligence and Statistics, AISTATS 2020, 26-28 August 2020, Online [Palermo, Sicily, Italy], pp. 277–287, PMLR, 2020.
2019
Fairness Constraints: A Flexible Approach for Fair Classification Journal Article
In: J. Mach. Learn. Res., vol. 20, pp. 75:1–75:42, 2019.
One-Network Adversarial Fairness Proceedings Article
In: The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, The Thirty-First Innovative Applications of Artificial Intelligence Conference, IAAI 2019, The Ninth AAAI Symposium on Educational Advances in Artificial Intelligence, EAAI 2019, Honolulu, Hawaii, USA, January 27 - February 1, 2019, pp. 2412–2420, AAAI Press, 2019.
2018
Enhancing the Accuracy and Fairness of Human Decision Making Proceedings Article
In: Bengio, Samy; Wallach, Hanna M.; Larochelle, Hugo; Grauman, Kristen; Cesa-Bianchi, Nicolò; Garnett, Roman (Ed.): Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, NeurIPS 2018, December 3-8, 2018, Montréal, Canada, pp. 1774–1783, 2018.
2017
Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatment Proceedings Article
In: Barrett, Rick; Cummings, Rick; Agichtein, Eugene; Gabrilovich, Evgeniy (Ed.): Proceedings of the 26th International Conference on World Wide Web, WWW 2017, Perth, Australia, April 3-7, 2017, pp. 1171–1180, ACM, 2017.
Fairness Constraints: Mechanisms for Fair Classification Proceedings Article
In: Singh, Aarti; Zhu, Xiaojin (Jerry) (Ed.): Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, AISTATS 2017, 20-22 April 2017, Fort Lauderdale, FL, USA, pp. 962–970, PMLR, 2017.
From Parity to Preference-based Notions of Fairness in Classification Proceedings Article
In: Guyon, Isabelle; Luxburg, Ulrike; Bengio, Samy; Wallach, Hanna M.; Fergus, Rob; Vishwanathan, S. V. N.; Garnett, Roman (Ed.): Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pp. 229–239, 2017.