Decentralized Federated Learning with Prototype Exchange
Mathematics · 12.01.2025 · 13 (2) · 237
DOI: 10.3390/math13020237 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 12.01.2025. Verfasst von Lu Qi und 5 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
As AI applications become increasingly integrated into daily life, protecting user privacy while enabling collaborative model training has become a crucial challenge, especially in decentralized edge computing environments. Traditional federated learning (FL) approaches, which rely on centralized model aggregation, struggle in such settings due to bandwidth limitations, data heterogeneity, and varying device capabilities among edge nodes. To address these issues, we propose PearFL, a decentralized FL framework that enhances collaboration and model generalization by introducing prototype exchange mechanisms. PearFL allows each client to share lightweight prototype information with its neighbors, minimizing communication overhead and improving model consistency across distributed devices. Experimental evaluations on benchmark datasets, including MNIST, CIFAR-10, and CIFAR-100, demonstrate that PearFL achieves superior communication efficiency, convergence speed, and accuracy compared to conventional FL methods. These results confirm PearFL’s efficacy as a scalable solution for decentralized learning in heterogeneous and resource-constrained environments.
Zitieren
APA
Qi, L., Chen, H., Zou, H., Chen, S., Zhang, X., & Chen, H. (2025). Decentralized Federated Learning with Prototype Exchange. Mathematics, 13(2), 237. https://doi.org/10.3390/math13020237
Vancouver
Qi L, Chen H, Zou H, Chen S, Zhang X, Chen H. Decentralized Federated Learning with Prototype Exchange. Mathematics. 2025;13(2):237. doi:10.3390/math13020237
BibTeX
@article{Qi2025,
author = {Qi, Lu and Chen, Haoze and Zou, Hongliang and Chen, Shaohua and Zhang, Xiaoying and Chen, Hongyan},
title = {Decentralized Federated Learning with Prototype Exchange},
journal = {Mathematics},
year = {2025},
volume = {13},
number = {2},
pages = {237},
doi = {10.3390/math13020237}
}
EUVIMED