FedDRL: trustworthy federated learning model fusion method based on staged reinforcement learning

FedDRL: trustworthy federated learning model fusion method based on staged reinforcement learning

Federated learning facilitates collaborative data analysis among multiple participants while preserving user privacy. However, conventional federated learning approaches, typically employing weighted average techniques for model fusion, confront two significant challenges: 1. The inclusion of malici...

Full description

Bibliographic Details
Main Authors: Chen, Leiming, Zhang, Weishan, Dong, Cihao, Huang, Ziling, Nie, Yuming, Hou, Zhaoxiang, Qiao, Sibo, Tan, Chee Wei
Other Authors: School of Computer Science and Engineering
Format: Journal Article
Language:English
Published: 2024
Subjects:
Computer and Information Science
Federated learning
Model attack
Online Access:https://hdl.handle.net/10356/179933

Internet

https://hdl.handle.net/10356/179933

Similar Items