Back to search

University of Birmingham

Class imbalance in Federated Learning

Abstract

dc:description.abstract

Federated Learning (FL) is a distributed and privacy protected machine learning paradigm that trains a global model across multiple clients without gathering their local data. Class imbalance is a common issue in machine learning, where the number of samples in each class is not balanced. In the field of federated learning, class imbalance is one of the key challenges that undermine the performance of the global model. Concentrating on the class imbalance problems in FL, this thesis investigates the scenarios and corresponding impacts, explores the mechanisms behind the issues, and proposes effective solutions from different perspectives. At the beginning, two metrics are proposed to quantify the issue from the global and local perspectives. After that, a novel resampling methods utilizing both minority and majority classes are proposed to address the class imbalance in distributed settings. The proposed methods are robust and effective in severe class imbalance scenarios and small datasets. Worse case in FL is the inter-client class imbalance, which refers to the class distribution mismatch between clients, sometimes also known as data heterogeneity. This mismatch results in catastrophic forgetting in local training on the minority class, slowing down the convergence of the global model. By analysing back-propagation with class imbalance, Error Asymmetry is identified as the root cause of catastrophic forgetting. By connecting the Error Asymmetry with gradient, a novel gradient alignment method is proposed to mitigate the issue. Furthermore, advanced optimization techniques show promising results in addressing the class imbalance in federated learning. A new momentum based optimization algorithm is proposed to improve the speed-up the training by applying a reverse exponential moving average on the gradient. Experiments show the effectiveness of the proposed methods in addressing the data heterogeneity.

Degree

thesis:*
Name dc:type.qualificationname
d_ph
Level dc:type.qualificationlevel
d_ph
Grantor dc:publisher.institution
University of Birmingham
Year dc:date.issued
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Xiao, Chenguang

Subjects

dc:subject × 1

Rights

Language dc:language.dcterms_iso639_2
eng

Chain of custody

source
Harvested from
University of Birmingham
Base URL
etheses.bham.ac.uk/cgi/oai2
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Xiao, Chenguang. Class imbalance in Federated Learning. d_ph thesis, University of Birmingham, 2025.