Algorithms for Resolving Heterogeneity in Federated Learning

DOI

10.2991/978-94-6463-823-3_102How to use a DOI?

Keywords

Heterogeneity; Optimization algorithms; Classification

Abstract

From centralized learning to distributed learning, data encountered a explosive growth. As distributed learning became very popular in a large number of areas, people began to care about the privacy issue. In order to dispel people’s concerns, federated learning was introduced. By the idea of “models exchange but data holds still”, the new technique really solved the privacy problem. However, the framework of classic federated learning algorithm which is known as FedAvg (Federated Averaging), still has some defects like heterogeneity. In response to settle the heterogeneous setbacks, plentiful methods were proposed by other authors and they are really distinct from each other, so this paper introduces some well-known algorithms and some new techniques, concludes them into three types and makes comparative analysis to discuss their similarities and personalities pairs by pairs. This study provides a clear classification of federated learning methods, which can make those who initially contact the federated learning a clearer understanding about it.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Shenhao Wang
PY  - 2025
DA  - 2025/08/31
TI  - Algorithms for Resolving Heterogeneity in Federated Learning
BT  - Proceedings of the 2025 3rd International Conference on Image, Algorithms, and Artificial Intelligence (ICIAAI 2025)
PB  - Atlantis Press
SP  - 1058
EP  - 1069
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-823-3_102
DO  - 10.2991/978-94-6463-823-3_102
ID  - Wang2025
ER  -