Federated Learning Meets Multi-Objective Optimization

• Published in: IEEE transactions on network science and engineering Vol. 9; no. 4; pp. 2039 - 2051
• Main Authors: Hu, Zeou, Shaloudegi, Kiarash, Zhang, Guojun, Yu, Yaoliang
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.07.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Arithmetic; Collaborative work; Convergence; Distributed algorithms; Edge computing; Federated learning; Machine learning; Machine learning algorithms; Multiple objective analysis; Neural networks; Optimization; Pareto optimization; Robustness; Servers
• ISSN: 2327-4697; 2334-329X
• DOI: 10.1109/TNSE.2022.3169117

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 algorithm FedMGDA+ 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 any participating user. We establish the convergence properties of FedMGDA+ and point out its connections to existing approaches. Extensive experiments on a variety of datasets confirm that FedMGDA+ compares favorably against state-of-the-art.