Towards Bilateral Client Selection in Federated Learning Using Matching Game Theory

Osama Wehbi, Sarhad Arisdakessian, Omar Abdel Wahab, Hadi Otrok, Safa Otoum, Azzam Mourad

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

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.

Original languageBritish English
Title of host publication2022 IEEE Global Communications Conference, GLOBECOM 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2764-2769
Number of pages6
ISBN (Electronic)9781665435406
DOIs
StatePublished - 2022
Event2022 IEEE Global Communications Conference, GLOBECOM 2022 - Virtual, Online, Brazil
Duration: 4 Dec 20228 Dec 2022

Publication series

Name2022 IEEE Global Communications Conference, GLOBECOM 2022 - Proceedings

Conference

Conference2022 IEEE Global Communications Conference, GLOBECOM 2022
Country/TerritoryBrazil
CityVirtual, Online
Period4/12/228/12/22

Keywords

  • Client Selection
  • Federated Learning
  • Internet of Things (IoT)
  • Matching Game Theory
  • Pricing

Fingerprint

Dive into the research topics of 'Towards Bilateral Client Selection in Federated Learning Using Matching Game Theory'. Together they form a unique fingerprint.

Cite this