Citation

Chen, Jian and Zhang, Peifeng and Chen, Jiahui and Lau, Terry Shue Chien (2024) Heterogeneity-Aware Clustering and Intra-Cluster Uniform Data Sampling for Federated Learning. IEEE Transactions on Emerging Topics in Computational Intelligence. pp. 1-12. ISSN 2471-285X

Text Heterogeneity-Aware Clustering and Intra-Cluster Uniform Data Sampling for Federated Learning.pdf - Published Version Restricted to Repository staff only Download (2MB)

Abstract

Federated learning (FL) is an innovative privacypreserving machine learning paradigm that enables clients to train a global model without sharing their local data. However, the coexistence of category distribution heterogeneity and quantity imbalance frequently occurs in real-world FL scenarios. On the one side, due to the category distribution heterogeneity, local models are optimized based on distinct local objectives, resulting in divergent optimization directions. On the other side, quantity imbalance in widely used uniform client sampling of FL may hinder the active participation of clients with larger datasets in model training, and potentially make the model get suboptimal performance. To tackle this, we propose a framework that incorporates heterogeneityaware clustering and intra-cluster uniform data sampling. More precisely, we firstly do heterogeneity-aware clustering that performs clustering on clients based on category distribution vectors. Then, we implement intra-cluster uniform data sampling, where local data from each client within a cluster is randomly selected based on a predetermined probability. Furthermore, to address privacy concerns, we incorporate homomorphic encryption to protect clients’ category distribution vectors and sample sizes. Finally, the experimental results on multiple benchmark datasets demonstrate that the e proposed framework validate the superiority of our approach.

Item Type:	Article
Uncontrolled Keywords:	Federated learning, quantity imbalance, category distribution heterogeneity.
Subjects:	L Education > LB Theory and practice of education > LB1060 Learning Q Science > QA Mathematics > QA71-90 Instruments and machines
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	13 Jan 2025 05:01
Last Modified:	13 Jan 2025 05:01
URII:	http://shdl.mmu.edu.my/id/eprint/13328

Downloads

Edit (login required)