Balancing Fairness and Robustness via Partial Invariance

TL;DR

This paper proposes a partial invariance approach to improve out-of-distribution generalization by balancing fairness and robustness, especially when the traditional IRM assumptions do not hold.

Contribution

It introduces a hierarchical partial invariance framework that enforces local invariance within environment partitions to address limitations of IRM.

Findings

Partial invariance alleviates the fairness-robustness trade-off.

Framework improves OOD generalization in hierarchical data.

Method is effective in classification with causal distribution shifts.

Abstract

The Invariant Risk Minimization (IRM) framework aims to learn invariant features from a set of environments for solving the out-of-distribution (OOD) generalization problem. The underlying assumption is that the causal components of the data generating distributions remain constant across the environments or alternately, the data "overlaps" across environments to find meaningful invariant features. Consequently, when the "overlap" assumption does not hold, the set of truly invariant features may not be sufficient for optimal prediction performance. Such cases arise naturally in networked settings and hierarchical data-generating models, wherein the IRM performance becomes suboptimal. To mitigate this failure case, we argue for a partial invariance framework. The key idea is to introduce flexibility into the IRM framework by partitioning the environments based on hierarchical differences, while enforcing invariance locally within the partitions. We motivate this framework in classification settings with causal distribution shifts across environments. Our results show the capability of the partial invariant risk minimization to alleviate the trade-off between fairness and risk in certain settings.