Fair Domain Generalization: An Information-Theoretic View

TL;DR

This paper introduces an information-theoretic framework for fair domain generalization, proposing a Pareto optimization method that balances utility and fairness in unseen domains, validated on vision and language datasets.

Contribution

It derives mutual information-based bounds for risk and fairness, and proposes PAFDG, a novel Pareto-optimization approach for fair domain generalization.

Findings

PAFDG outperforms existing methods in utility-fairness trade-offs.

Theoretical bounds guide the design of fair domain generalization algorithms.

Experiments demonstrate effectiveness on real-world vision and language datasets.

Abstract

Domain generalization (DG) and algorithmic fairness are two critical challenges in machine learning. However, most DG methods focus only on minimizing expected risk in the unseen target domain without considering algorithmic fairness. Conversely, fairness methods typically do not account for domain shifts, so the fairness achieved during training may not generalize to unseen test domains. In this work, we bridge these gaps by studying the problem of Fair Domain Generalization (FairDG), which aims to minimize both expected risk and fairness violations in unseen target domains. We derive novel mutual information-based upper bounds for expected risk and fairness violations in multi-class classification tasks with multi-group sensitive attributes. These bounds provide key insights for algorithm design from an information-theoretic perspective. Guided by these insights, we introduce PAFDG (Pareto-Optimal Fairness for Domain Generalization), a practical framework that solves the FairDG problem and models the utility-fairness trade-off through Pareto optimization. Experiments on real-world vision and language datasets show that PAFDG achieves superior utility-fairness trade-offs compared to existing methods.