Fairness and robustness in anti-causal prediction

TL;DR

This paper explores the relationship between fairness and robustness in anti-causal prediction tasks, revealing how risk invariance and separation are connected through causal analysis, and demonstrating practical benefits in medical imaging.

Contribution

It establishes explicit links between fairness and robustness via causal reasoning, advocating for separation in anti-causal settings and showing robustness approaches can effectively enforce fairness.

Findings

Separation relates to risk invariance in anti-causal models.

Robustness methods often outperform direct fairness enforcement.

Empirical validation on pneumonia detection from X-rays.

Abstract

Robustness to distribution shift and fairness have independently emerged as two important desiderata required of modern machine learning models. While these two desiderata seem related, the connection between them is often unclear in practice. Here, we discuss these connections through a causal lens, focusing on anti-causal prediction tasks, where the input to a classifier (e.g., an image) is assumed to be generated as a function of the target label and the protected attribute. By taking this perspective, we draw explicit connections between a common fairness criterion - separation - and a common notion of robustness - risk invariance. These connections provide new motivation for applying the separation criterion in anticausal settings, and inform old discussions regarding fairness-performance tradeoffs. In addition, our findings suggest that robustness-motivated approaches can be used to enforce separation, and that they often work better in practice than methods designed to directly enforce separation. Using a medical dataset, we empirically validate our findings on the task of detecting pneumonia from X-rays, in a setting where differences in prevalence across sex groups motivates a fairness mitigation. Our findings highlight the importance of considering causal structure when choosing and enforcing fairness criteria.