Clustered Federated Learning with Adaptive Similarity for Non-IID Data
Electronics · 14.11.2025 · 14 (22) · 4454
DOI: 10.3390/electronics14224454 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 14.11.2025. Verfasst von Guodong Yi und 3 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: This research was funded by the National Key Research and Development Program of China.
Abstract (Originalsprache)
Federated learning (FL) offers a distributed approach for the collaborative training of machine learning models across decentralized clients while safeguarding data privacy. This characteristic makes FL well suited for privacy-sensitive fields such as healthcare and finance. However, addressing the heterogeneity caused by nonindependent and identically distributed (non-IID) data remains a significant challenge for traditional FL methods. To address these issues, the enhancing clustered federated learning with adaptive similarity (AS-CFL) algorithm, which dynamically forms client clusters based on model update similarity and uses a forward-incentive mechanism to improve collaborative training efficiency among similar clients, is proposed in this study. Experimental results on the MNIST and EMNIST datasets reveal that compared with baseline methods such as the CFL, IFCA, and FedAvg models, the AS-CFL algorithm achieves faster convergence—reducing the number of communication rounds by approximately 20%—while maintaining competitive accuracy, demonstrating its effectiveness in heterogeneous FL scenarios.
Förderung
- This research was funded by the National Key Research and Development Program of China
Zitieren
APA
Yi, G., Wu, Z., Zhang, X., & Li, X. (2025). Clustered Federated Learning with Adaptive Similarity for Non-IID Data. Electronics, 14(22), 4454. https://doi.org/10.3390/electronics14224454
Vancouver
Yi G, Wu Z, Zhang X, Li X. Clustered Federated Learning with Adaptive Similarity for Non-IID Data. Electronics. 2025;14(22):4454. doi:10.3390/electronics14224454
BibTeX
@article{Yi2025,
author = {Yi, Guodong and Wu, Zhouyang and Zhang, Xinyu and Li, Xiaocui},
title = {Clustered Federated Learning with Adaptive Similarity for Non-IID Data},
journal = {Electronics},
year = {2025},
volume = {14},
number = {22},
pages = {4454},
doi = {10.3390/electronics14224454}
}
EUVIMED