Proportional Fairness in Federated Learning

With the increasingly broad deployment of Federated Learning (FL) systems in the real world, it is critical but challenging to ensure fairness in FL, i.e. reasonably satisfactory performances for each of the numerous diverse clients. Motivated by its great success in wireless networks, in this work, we introduce and study Proportional Fairness (PF) in FL. By viewing FL from a cooperative game perspective, where the players (clients) collaboratively learn a good model, we formulate PF as Nash bargaining solutions. Based on this concept, we propose PropFair, a novel and easy-to-implement algorithm for finding fair solutions in FL, with its convergence proved. Through extensive experiments on a wide array of vision and language datasets, we demonstrate that PropFair consistently achieves a noticeable improvement of the worst 10% accuracy over state-of-the-art fair FL algorithms, while maintaining competitive overall performance.