Fairness-aware Federated Minimax Optimization with Convergence Guarantee

TL;DR

This paper introduces FFALM, a fairness-aware federated learning algorithm that incorporates a fairness constraint into the training process, ensuring group fairness with proven convergence guarantees and empirical validation on face datasets.

Contribution

It proposes a novel federated minimax optimization algorithm with convergence guarantees that explicitly addresses group fairness in heterogeneous data settings.

Findings

FFALM improves fairness on CelebA and UTKFace datasets.

Theoretical convergence rate bounds are established for FFALM.

Empirical results demonstrate enhanced fairness under data heterogeneity.

Abstract

Federated learning (FL) has garnered considerable attention due to its privacy-preserving feature. Nonetheless, the lack of freedom in managing user data can lead to group fairness issues, where models are biased towards sensitive factors such as race or gender. To tackle this issue, this paper proposes a novel algorithm, fair federated averaging with augmented Lagrangian method (FFALM), designed explicitly to address group fairness issues in FL. Specifically, we impose a fairness constraint on the training objective and solve the minimax reformulation of the constrained optimization problem. Then, we derive the theoretical upper bound for the convergence rate of FFALM. The effectiveness of FFALM in improving fairness is shown empirically on CelebA and UTKFace datasets in the presence of severe statistical heterogeneity.