.png){kind=icon}
Return
Federated Learning Meets Multi-Objective Optimization
.png){kind=icon}
OA
AI
DOI：10.1109/TNSE.2022.3169117.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
Optimization
Collaborative work
Servers
Robustness
Convergence
Machine learning algorithms
Arithmetic
Pareto optimization
Distributed algorithms
Federated learning
Edge computing
Machine learning
Neural networks
Journal
I
IF:
7.9
Papers:
2.6K
Citations:
10.0K
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveShareSaveEFFECT OF DROUGHT STRESS ON CHLOROPHYLL FLUORESCENCE, AND BIOMASS PORTIONING OF AEGILOPS TAUSCHII L.OAAI
OAAIShareSave
ShareSave
View more