EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

A Personalized Federated Learning Algorithm Based on Dynamic Weight Allocation

Yazhi Liu, Siwei Li, Wei Li, Hui Qian, Haonan Xia

Electronics · 2025-01-25 · 14 (3) · 484

DOI: 10.3390/electronics14030484 ↗

At a glance

Journal article in Electronics, published online on 2025-01-25. Written by Yazhi Liu and 4 co-authors. Cited 7 times so far (Crossref); 29 references. The full text is freely available (open access, CC BY 4.0). Funded by: the Science and Technology Project of the Hebei Education Department.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Federated learning is a privacy-preserving distributed machine learning paradigm. However, due to client data heterogeneity, the global model trained by a traditional federated averaging algorithm often exhibits poor generalization ability. To mitigate the impact of data heterogeneity, some existing research has proposed clustered federated learning, where clients with similar data distributions are grouped together to reduce interference from dissimilar clients. However, since the data distribution of clients is unknown, determining the optimal number of clusters is difficult, leading to reduced model convergence efficiency. To address this issue, this paper proposes a personalized federated learning algorithm based on dynamic weight allocation. First, each client is allowed to obtain a global model tailored to fit its local data distribution. During the client model aggregation process, the server first computes the similarity of model updates between clients and dynamically allocates aggregation weights to client models based on these similarities. Secondly, clients use the received exclusive global model to train their local models via the personalized federated learning algorithm. Extensive experimental results demonstrate that, compared to other personalized federated learning algorithms, the proposed method effectively improves model accuracy and convergence speed.

Funding

  • the Science and Technology Project of the Hebei Education Department

Cite

APA

Liu, Y., Li, S., Li, W., Qian, H., & Xia, H. (2025). A Personalized Federated Learning Algorithm Based on Dynamic Weight Allocation. Electronics, 14(3), 484. https://doi.org/10.3390/electronics14030484

Vancouver

Liu Y, Li S, Li W, Qian H, Xia H. A Personalized Federated Learning Algorithm Based on Dynamic Weight Allocation. Electronics. 2025;14(3):484. doi:10.3390/electronics14030484

BibTeX
@article{Liu2025,
  author = {Liu, Yazhi and Li, Siwei and Li, Wei and Qian, Hui and Xia, Haonan},
  title = {A Personalized Federated Learning Algorithm Based on Dynamic Weight Allocation},
  journal = {Electronics},
  year = {2025},
  volume = {14},
  number = {3},
  pages = {484},
  doi = {10.3390/electronics14030484}
}
Start for free →