A Personalized Federated Learning Method Based on Knowledge Distillation and Differential Privacy
Electronics · 06.09.2024 · 13 (17) · 3538
DOI: 10.3390/electronics13173538 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 06.09.2024. Verfasst von Yingrui Jiang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, China Postdoctoral Science Foundation funded project.
Abstract (Originalsprache)
Federated learning allows data to remain decentralized, and various devices work together to train a common machine learning model. This method keeps sensitive data local on devices, protecting privacy. However, privacy protection and non-independent and identically distributed data are significant challenges for many FL techniques currently in use. This paper proposes a personalized federated learning method (FedKADP) that integrates knowledge distillation and differential privacy to address the issues of privacy protection and non-independent and identically distributed data in federated learning. The introduction of a bidirectional feedback mechanism enables the establishment of an interactive tuning loop between knowledge distillation and differential privacy, allowing dynamic tuning and continuous performance optimization while protecting user privacy. By closely monitoring privacy overhead through Rényi differential privacy theory, this approach effectively balances model performance and privacy protection. Experimental results using the MNIST and CIFAR-10 datasets demonstrate that FedKADP performs better than conventional federated learning techniques, particularly when handling non-independent and identically distributed data. It successfully lowers the heterogeneity of the model, accelerates global model convergence, and improves validation accuracy, making it a new approach to federated learning.
Förderung
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation funded project
Zitieren
APA
Jiang, Y., Zhao, X., Li, H., & Xue, Y. (2024). A Personalized Federated Learning Method Based on Knowledge Distillation and Differential Privacy. Electronics, 13(17), 3538. https://doi.org/10.3390/electronics13173538
Vancouver
Jiang Y, Zhao X, Li H, Xue Y. A Personalized Federated Learning Method Based on Knowledge Distillation and Differential Privacy. Electronics. 2024;13(17):3538. doi:10.3390/electronics13173538
BibTeX
@article{Jiang2024,
author = {Jiang, Yingrui and Zhao, Xuejian and Li, Hao and Xue, Yu},
title = {A Personalized Federated Learning Method Based on Knowledge Distillation and Differential Privacy},
journal = {Electronics},
year = {2024},
volume = {13},
number = {17},
pages = {3538},
doi = {10.3390/electronics13173538}
}
EUVIMED