Blind Pareto Fairness and Subgroup Robustness

Natalia Martinez, Martin Bertran, Afroditi Papadaki, Miguel R. D. Rodrigues, Guillermo Sapiro

Keywords: fairness, fairness in machine learning, fairness without demographics, robustness, subgroup robustness, blind fairness, pareto fairness

Abstract: With the wide adoption of machine learning algorithms across various application domains, there is a growing interest in the fairness properties of such algorithms. The vast majority of the activity in the field of group fairness addresses disparities between predefined groups based on protected features such as gender, age, and race, which need to be available at train, and often also at test, time. These approaches are static and retrospective, since algorithms designed to protect groups identified a priori cannot anticipate and protect the needs of different at-risk groups in the future. In this work we analyze the space of solutions for worst-case fairness beyond demographics, and propose Blind Pareto Fairness (BPF), a method that leverages no-regret dynamics to recover a fair minimax classifier that reduces worst-case risk of any potential subgroup of sufficient size, and guarantees that the remaining population receives the best possible level of service. BPF addresses fairness beyond demographics, that is, it does not rely on predefined notions of at-risk groups, neither at train nor at test time. Our experimental results show that the proposed framework improves worst-case risk in multiple standard datasets, while simultaneously providing better levels of service for the remaining population, in comparison to competing methods.

One-sentence Summary: We analyze worst-case fairness beyond demographics, and propose Blind Pareto Fairness, a method that reduces worst-case risk of any subgroup of sufficient size, and guarantees that the remaining population receives the best possible level of service.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=aJlCPsiQKk