Fair Federated Learning via Bounded Group Loss
This addresses fairness constraints in federated learning applications, offering a provable solution for scenarios where prior methods lacked formal guarantees.
The paper tackled the problem of ensuring fair predictions across protected groups in federated learning by proposing a framework based on Bounded Group Loss, which provides convergence and fairness guarantees while improving accuracy over baselines in benchmarks.
Fair prediction across protected groups is an important constraint for many federated learning applications. However, prior work studying group fair federated learning lacks formal convergence or fairness guarantees. 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. 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 baseline approaches.