CPPer-FL: Clustered Parallel Training for Efficient Personalized Federated Learning
IEEE Transactions on Mobile Computing · 2024-10 · 23 (10) · 9424-9436
DOI: 10.1109/tmc.2024.3365951 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2024-10. Verfasst von Ran Zhang und 6 weiteren Autor:innen. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
In this paper, a clustered parallel training algorithm is designed for personalized federated learning (Per-FL), called CPPer-FL. CPPer-FL improves the communication and training efficiency of Per-FL from two perspectives, namely, less burden for the central server and lower interaction idling delay. CPPer-FL adopts a client-edge-center learning architecture, which offloads the central server's model aggregation and communication burden to distributed edge servers. Also, CPPer-FL redesigns the cascading model synchronization and updating procedure in conventional Per-FL and changes it to a parallel manner, thus improving the interaction efficiency in the training process. Further, for the proposed hierarchical architecture, two approaches are proposed to cater to Per-FL: similarity-based clustering for client-edge association and personalized model aggregation for parallel model updating, such that clients’ personal features can be preserved in the training process. The convergence of CPPer-FL has been formally analyzed and proved. Evaluation results validate the communication efficiency, model convergence, and model accuracy improvement.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Zhang, R., Liu, F., Liu, J., Chen, M., Tang, Q., Huang, T., & Yu, F. R. (2024). CPPer-FL: Clustered Parallel Training for Efficient Personalized Federated Learning. IEEE Transactions on Mobile Computing, 23(10), 9424-9436. https://doi.org/10.1109/tmc.2024.3365951
Vancouver
Zhang R, Liu F, Liu J, Chen M, Tang Q, Huang T, et al. CPPer-FL: Clustered Parallel Training for Efficient Personalized Federated Learning. IEEE Transactions on Mobile Computing. 2024;23(10):9424-9436. doi:10.1109/tmc.2024.3365951
BibTeX
@article{Zhang2024,
author = {Zhang, Ran and Liu, Fangqi and Liu, Jiang and Chen, Mingzhe and Tang, Qinqin and Huang, Tao and Yu, F. Richard},
title = {CPPer-FL: Clustered Parallel Training for Efficient Personalized Federated Learning},
journal = {IEEE Transactions on Mobile Computing},
year = {2024},
volume = {23},
number = {10},
pages = {9424--9436},
doi = {10.1109/tmc.2024.3365951}
}
EUVIMED