Toward Federated Learning With Byzantine and Inactive Users: A Game Theory Approach

Toward Federated Learning With Byzantine and Inactive Users: A Game Theory Approach

Federated learning (FL) can guarantee privacy by allowing local users only upload their training models to central server (CS). However, the existence of Byzantine or inactive users may cause model corruption or inactively participation in FL. In this paper, a game theory based detection and incenti...

Full description

Bibliographic Details
Main Authors: Xiangyu Chen, Peng Lan, Zhongchang Zhou, Angran Zhao, Pengfei Zhou, Fenggang Sun
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Federated learning
differential aggregate gradient descent
random Euclidean distance
game theory
Online Access:https://ieeexplore.ieee.org/document/10089457/

Internet

https://ieeexplore.ieee.org/document/10089457/

Similar Items