Fair Federated Learning via Bounded Group Loss

Fair prediction across protected groups is an important consideration in federated learning applications. In this work we propose a general framework for provably fair federated learning. In particular, we explore and extend the notion of Bounded Group Loss as a theoretically-grounded approach for group fairness that offers favorable trade-offs between fairness and utility relative to prior work. Using this setup, we propose a scalable federated optimization method that optimizes the empirical risk under a number of group fairness constraints. We provide convergence guarantees for the method as well as fairness guarantees for the resulting solution. Empirically, we evaluate our method across common benchmarks from fair ML and federated learning, showing that it can provide both fairer and more accurate predictions than existing approaches in fair federated learning.