GIFAIR-FL: A Framework for Group and Individual Fairness in Federated Learning

TL;DR

GIFAIR-FL is a federated learning framework that enforces group and individual fairness through regularization, ensuring fairer client outcomes without sacrificing accuracy, applicable to both global and personalized models.

Contribution

The paper introduces GIFAIR-FL, a novel federated learning algorithm that incorporates fairness regularization and provides theoretical convergence guarantees for various data distributions.

Findings

Improved fairness in image classification and text prediction tasks.

Maintains comparable or superior prediction accuracy.

Converges in non-convex and strongly convex settings.

Abstract

In this paper we propose \texttt{GIFAIR-FL}: a framework that imposes \textbf{G}roup and \textbf{I}ndividual \textbf{FAIR}ness to \textbf{F}ederated \textbf{L}earning settings. By adding a regularization term, our algorithm penalizes the spread in the loss of client groups to drive the optimizer to fair solutions. Our framework \texttt{GIFAIR-FL} can accommodate both global and personalized settings. Theoretically, we show convergence in non-convex and strongly convex settings. Our convergence guarantees hold for both $i.i.d.$ and non-$i.i.d.$ data. To demonstrate the empirical performance of our algorithm, we apply our method to image classification and text prediction tasks. Compared to existing algorithms, our method shows improved fairness results while retaining superior or similar prediction accuracy.