FEED: Fairness-Enhanced Meta-Learning for Domain Generalization

TL;DR

This paper presents FEED, a novel meta-learning framework that enhances domain generalization by incorporating fairness constraints through disentangled data representations, leading to models that generalize well across diverse domains while maintaining fairness.

Contribution

The paper introduces FEED, a fairness-aware meta-learning approach that disentangles data into content, style, and sensitive features to improve domain generalization with fairness considerations.

Findings

FEED outperforms existing methods in accuracy and fairness across benchmarks.

Disentangling representations improves robustness to domain shifts.

Incorporating fairness constraints enhances generalization without sacrificing performance.

Abstract

Generalizing to out-of-distribution data while being aware of model fairness is a significant and challenging problem in meta-learning. The goal of this problem is to find a set of fairness-aware invariant parameters of classifier that is trained using data drawn from a family of related training domains with distribution shift on non-sensitive features as well as different levels of dependence between model predictions and sensitive features so that the classifier can achieve good generalization performance on unknown but distinct test domains. To tackle this challenge, existing state-of-the-art methods either address the domain generalization problem but completely ignore learning with fairness or solely specify shifted domains with various fairness levels. This paper introduces an approach to fairness-aware meta-learning that significantly enhances domain generalization capabilities. Our framework, Fairness-Enhanced Meta-Learning for Domain Generalization (FEED), disentangles latent data representations into content, style, and sensitive vectors. This disentanglement facilitates the robust generalization of machine learning models across diverse domains while adhering to fairness constraints. Unlike traditional methods that focus primarily on domain invariance or sensitivity to shifts, our model integrates a fairness-aware invariance criterion directly into the meta-learning process. This integration ensures that the learned parameters uphold fairness consistently, even when domain characteristics vary widely. We validate our approach through extensive experiments across multiple benchmarks, demonstrating not only superior performance in maintaining high accuracy and fairness but also significant improvements over existing state-of-the-art methods in domain generalization tasks.