App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 9

Prototypical network-based hierarchical pre-clustered federated learning framework

Wang Jinsong1,2,3
Wei Zongpu1,2,3
Zhao Zening1,2,3
1. School of Computer Science & Engineering, Tianjin University of Technology, Tianjin 300382, China
2. Tianjin Key Laboratory of Intelligence Computing & Novel Software Technology, Tianjin 300382, China
3. National Engineering Laboratory for Computer Virus Prevention & Control Technology, Tianjin 300457, China
DOI: 10.19734/j.issn.1001-3695.2025.11.0534

Abstract

To address the issues of high coupling, knowledge silos across clusters and single-metric similarity in clustered federated learning, this paper proposed a prototypical network-based hierarchical pre-clustered federated learning framework named ProtoCFL. First, the framework designed three phases: per-clustering, main training and trigger-based re-clustering phases and decoupled clustering from training, enabling flexible deployment. Second, it proposed a split binary tree-based clustering method, which recursively partitioned clusters while incorporating global knowledge from the root, thereby improving model generalization. Third, it proposed a prototype similarity metric that fused the label distribution and the feature prototype, accurately quantifying client similarity. Extensive experiments on FashionMNIST, CIFAR10, and AGNews demonstrated that ProtoCFL improved accuracy by up to 3.28%, 9.45%, and 7.39%, respectively, compared to existing frameworks, thereby offering an efficient and high-accuracy solution for clustered federated learning.

Foundation Support

国家自然科学基金面上项目(62572350)
天津市重点研发计划(23YFZCSN00240)
天津市技术创新引导专项基金资助项目(22YDPYGX00040)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.11.0534
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 9

Publish History

[2026-05-29] Accepted Paper

Cite This Article

王劲松, 魏宗朴, 赵泽宁. 基于原型网络的层次预聚类联邦学习框架 [J]. 计算机应用研究, 2026, 43 (9). (2026-06-02). https://doi.org/10.19734/j.issn.1001-3695.2025.11.0534. (Wang Jinsong, Wei Zongpu, Zhao Zening. Prototypical network-based hierarchical pre-clustered federated learning framework [J]. Application Research of Computers, 2026, 43 (9). (2026-06-02). https://doi.org/10.19734/j.issn.1001-3695.2025.11.0534. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)