Fair Domain Generalization: An Information-Theoretic View
This addresses the critical challenge of ensuring fairness in machine learning models that generalize across domains, which is important for deploying fair AI in diverse real-world settings, though it builds incrementally on existing DG and fairness methods.
The paper tackles the combined problem of domain generalization and algorithmic fairness, aiming to minimize both expected risk and fairness violations in unseen target domains. It introduces PAFDG, a framework that achieves superior utility-fairness trade-offs on real-world vision and language datasets.
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.