Back to Search Start Over

FEDDRL: TRUSTWORTHY FEDERATED LEARNING MODEL FUSION METHOD BASED ON STAGED REINFORCEMENT LEARNING.

FEDDRL: TRUSTWORTHY FEDERATED LEARNING MODEL FUSION METHOD BASED ON STAGED REINFORCEMENT LEARNING.

Authors :
Leiming CHEN
Weishan ZHANG
Cihao DONG
Ziling HUANG
Yuming NIE
Zhaoxiang HOU
Sibo QIAO
Chee Wei TAN
Source :
Computing & Informatics; 2024, Vol. 43 Issue 1, p1-37, 37p
Publication Year :
2024

Abstract

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 malicious models in the fusion process can drastically undermine the accuracy of the aggregated global model. 2. Due to the heterogeneity problem of devices and data, the number of client samples does not determine the weight value of the model. To solve those challenges, we propose a trustworthy model fusion method based on reinforcement learning (FedDRL), which includes two stages. In the first stage, we propose a reliable client selection mechanism to exclude malicious models from the fusion process. In the second stage, we propose an adaptive model fusion method that dynamically assigns weights based on model quality to aggregate the best global models. Finally, we validate our approach against five distinct model fusion scenarios, demonstrating that our algorithm significantly enhanced reliability without compromising accuracy. [ABSTRACT FROM AUTHOR]

Subjects

Subjects :
FEDERATED learning
DATA analysis

Details

Language :
English
ISSN :
13359150
Volume :
43
Issue :
1
Database :
Supplemental Index
Journal :
Computing & Informatics
Publication Type :
Academic Journal
Accession number :
177332466
Full Text :
https://doi.org/10.31577/cai_2024_1_1