Skip to main content
Top
Published in:

01-04-2025

Mitigating bias in heterogeneous federated learning via stratified client selection

Authors: Yazhi Liu, Haonan Xia, Wei Li, Teng Niu

Published in: Peer-to-Peer Networking and Applications | Issue 2/2025

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

The article introduces a sophisticated client selection strategy for Federated Learning (FL) to tackle the challenges of data and system heterogeneity. It proposes the FedHD algorithm, which uses stratified sampling and Multi-Armed Bandit (MAB) to mitigate bias and ensure fair client participation. The approach reduces sampling variance and approximates the global data distribution, leading to improved convergence and model accuracy. The paper also highlights extensive experimental results demonstrating the superiority of FedHD over existing FL methods. The innovative combination of stratified sampling and MAB makes this work particularly valuable for enhancing the performance and fairness of FL systems.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Business + Economics & Engineering + Technology"

Online-Abonnement

Springer Professional "Business + Economics & Engineering + Technology" gives you access to:

  • more than 102.000 books
  • more than 537 journals

from the following subject areas:

  • Automotive
  • Construction + Real Estate
  • Business IT + Informatics
  • Electrical Engineering + Electronics
  • Energy + Sustainability
  • Finance + Banking
  • Management + Leadership
  • Marketing + Sales
  • Mechanical Engineering + Materials
  • Insurance + Risk


Secure your knowledge advantage now!

Springer Professional "Engineering + Technology"

Online-Abonnement

Springer Professional "Engineering + Technology" gives you access to:

  • more than 67.000 books
  • more than 390 journals

from the following specialised fileds:

  • Automotive
  • Business IT + Informatics
  • Construction + Real Estate
  • Electrical Engineering + Electronics
  • Energy + Sustainability
  • Mechanical Engineering + Materials





 

Secure your knowledge advantage now!

Springer Professional "Business + Economics"

Online-Abonnement

Springer Professional "Business + Economics" gives you access to:

  • more than 67.000 books
  • more than 340 journals

from the following specialised fileds:

  • Construction + Real Estate
  • Business IT + Informatics
  • Finance + Banking
  • Management + Leadership
  • Marketing + Sales
  • Insurance + Risk



Secure your knowledge advantage now!

Literature
This content is only visible if you are logged in and have the appropriate permissions.
Metadata
Title
Mitigating bias in heterogeneous federated learning via stratified client selection
Authors
Yazhi Liu
Haonan Xia
Wei Li
Teng Niu
Publication date
01-04-2025
Publisher
Springer US
Published in
Peer-to-Peer Networking and Applications / Issue 2/2025
Print ISSN: 1936-6442
Electronic ISSN: 1936-6450
DOI
https://doi.org/10.1007/s12083-024-01886-6

Premium Partner