E2FL: Equal and Equitable Federated Learning
It addresses fairness problems for data owners in federated learning, though it appears incremental as it builds on existing FL methods.
The paper tackles the fairness issue in Federated Learning caused by data heterogeneity, proposing E2FL to concurrently preserve equity and equality, and shows it outperforms baselines in efficiency and fairness across groups and individual clients.
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.