E2FL: Equal and Equitable Federated Learning

TL;DR

E2FL introduces a novel federated learning approach that simultaneously ensures fairness and equity among clients, addressing data heterogeneity issues to produce more balanced models.

Contribution

The paper proposes E2FL, a new federated learning method that maintains fairness properties, improving upon existing approaches in efficiency and fairness across groups and clients.

Findings

E2FL outperforms baselines in efficiency.

E2FL achieves better fairness among groups.

E2FL enhances fairness among individual clients.

Abstract

Federated Learning (FL) enables data owners to train a shared global model without sharing their private data. Unfortunately, FL is susceptible to an intrinsic fairness issue: due to heterogeneity in clients' data distributions, the final trained model can give disproportionate advantages across the participating clients. In this work, we present Equal and Equitable Federated Learning (E2FL) to produce fair federated learning models by preserving two main fairness properties, equity and equality, concurrently. We validate the efficiency and fairness of E2FL in different real-world FL applications, and show that E2FL outperforms existing baselines in terms of the resulting efficiency, fairness of different groups, and fairness among all individual clients.