Fairness-Aware Meta-Learning via Nash Bargaining

TL;DR

This paper proposes a novel meta-learning framework using Nash Bargaining to balance fairness and performance in machine learning models, effectively resolving hypergradient conflicts and improving fairness across multiple datasets.

Contribution

It introduces a two-stage meta-learning approach with Nash Bargaining for hypergradient conflict resolution, supported by theoretical proofs and empirical validation across diverse datasets.

Findings

Effective hypergradient conflict resolution with Nash Bargaining

Improved fairness metrics across multiple datasets

Theoretical guarantees of Pareto improvement and monotonic loss reduction

Abstract

To address issues of group-level fairness in machine learning, it is natural to adjust model parameters based on specific fairness objectives over a sensitive-attributed validation set. Such an adjustment procedure can be cast within a meta-learning framework. However, naive integration of fairness goals via meta-learning can cause hypergradient conflicts for subgroups, resulting in unstable convergence and compromising model performance and fairness. To navigate this issue, we frame the resolution of hypergradient conflicts as a multi-player cooperative bargaining game. We introduce a two-stage meta-learning framework in which the first stage involves the use of a Nash Bargaining Solution (NBS) to resolve hypergradient conflicts and steer the model toward the Pareto front, and the second stage optimizes with respect to specific fairness goals. Our method is supported by theoretical results, notably a proof of the NBS for gradient aggregation free from linear independence assumptions, a proof of Pareto improvement, and a proof of monotonic improvement in validation loss. We also show empirical effects across various fairness objectives in six key fairness datasets and two image classification tasks.