FedTrans

Client-transparent utility estimation for robust federated learning

Poster (2024)
Author(s)

M. Yang (TU Delft - Embedded Systems)

R. Zhu (TU Delft - Embedded Systems)

Q. Wang (TU Delft - Embedded Systems)

Jie Yang (TU Delft - Web Information Systems)

Research Group
Embedded Systems
More Info
expand_more
Publication Year
2024
Language
English
Research Group
Embedded Systems
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Federated Learning (FL) is an important privacy-preserving learning paradigm that plays an important role in the Intelligent Internet of Things. Training a global model in FL, however, is vulnerable to the data noise across the clients. In this paper, we introduce FedTrans, a novel client-transparent client utility estimation method designed to guide client selection for noisy scenarios, mitigating performance degradation problems. To estimate the client utility, we propose a Bayesian framework that models client utility and its relationships with the weight parameters and the performance of local models. We then introduce a variational inference algorithm to effectively infer client utility at the FL server, given only a small amount of auxiliary data. Our evaluation results demonstrate that leveraging FedTrans to select the clients can improve the accuracy performance (up to 7.8%), ensuring the robustness of FL in noisy scenarios.

Files

19141.png
(png | 1 Mb)
License info not available