Towards Bilateral Client Selection in Federated Learning Using Matching Game Theory

Document Type

Conference Proceeding

Source of Publication

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

Publication Date

12-8-2022

Abstract

Federated Learning (FL) is a novel distributed privacy-preserving learning paradigm, which enables the collaboration among several devices. However, selecting the participants that would contribute to this collaborative training is highly challenging. Adopting a random selection strategy would entail substantial problems due to the heterogeneity in terms of data quality and resources across the participants. To overcome this problem, we propose an intelligent client selection approach for federated learning on IoT devices using matching game theory. Our solution involves the design of: (1) preference functions for the client IoT devices and federated servers to allow them to rank each other according to several criteria such as accuracy and price, and (2) intelligent matching algorithms that take into account the preferences of both parties in their design. Based on our simulation findings, our strategy surpasses the VanillaFL selection approach in terms of maximizing both the revenues of the client devices and accuracy of the global federated learning model.

ISBN

978-1-6654-3540-6

Publisher

IEEE

Volume

00

First Page

01

Last Page

06

Disciplines

Computer Sciences

Keywords

Training, Federated learning, Simulation, Data integrity, Collaboration, Games, Servers

Indexed in Scopus

no

Open Access

no

Link to Full Text

Share

COinS