@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}
}
