Federated Learning Meets Multi-Objective Optimization
Zeou Hu, Kiarash Shaloudegi, Guojun Zhang, Yaoliang Yu · IEEE Transactions on Network Science and Engineering · 2022
Federated learning has emerged as a promising, massively distributed way to train a joint deep model over large amounts of edgedevices while keeping private user data strictly on device. In this work, motivated from ensuring fairness among users and robustness against malicious adversaries, we formulate federated learning as multi-objective optimization and propose a new algorithmFedMGDA+that is guaranteed to converge to Pareto stationary solutions.FedMGDA+is simple to implement, has fewer hyperparameters to tune, and refrains from sacrificing the performance of anyparticipatinguser. We establish the convergence properties ofFedMGDA+and point out its connections to existing approaches. Extensive experiments on a variety of datasets confirm thatFedMGDA+compares favorably against state-of-the-art.