App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 7

Personalized federated learning based on biorthogonal decomposition and adaptive aggregation

Shi Caijuan1,2
Zhu Hongli1,2
Li Baofeng1,2
Cheng Zheng1,2
Duan Changyu1
Yan Xiaodong1
1. College of Artificial Intelligence, North China University of Science and Technology, Tangshan Hebei 063210, China
2. Hebei Key Laboratory of Industrial Intelligent Perception, Tangshan Hebei 063210, China
DOI: 10.19734/j.issn.1001-3695.2025.09.0440

Abstract

To address the limited model personalization capability and degraded generalization performance caused by data heterogeneity in personalized federated learning (PFL) , this paper proposes FedBDAA (Federated learning based on Biorthogonal Decomposition and Adaptive Aggregation) . FedBDAA introduces a biorthogonal decomposition strategy that performs both functional and structural orthogonal decompositions on client model parameters. Meanwhile, it adopts a two-stage collaborative training approach to effectively extract and leverage local client data, thereby enhancing model personalization. Additionally, FedBDAA adopts an adaptive aggregation strategy that refines the magnitude and direction of the updated vectors of client-shared parameters, as well as dynamically adjusts aggregation weights to improve generalization. On the Cifar10, Cifar100 and Tiny-ImageNet datasets, the test accuracy of FedBDAA was 1.12%, 3.52% and 3.62% higher than that of the suboptimal algorithms pFedFDA, FedCP and FedALA respectively, verifying its effectiveness.

Foundation Support

北京市现代信息科学与网络技术重点实验室开放课题(XDXX2301)
华北理工大学杰出青年基金资助项目(JQ201715)
唐山市人才项目(A202110011)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.09.0440
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 7

Publish History

[2026-03-26] Accepted Paper

Cite This Article

史彩娟, 朱宏利, 李保锋, 等. 双正交分解与自适应聚合的个性化联邦学习 [J]. 计算机应用研究, 2026, 43 (7). (2026-03-27). https://doi.org/10.19734/j.issn.1001-3695.2025.09.0440. (Shi Caijuan, Zhu Hongli, Li Baofeng, et al. Personalized federated learning based on biorthogonal decomposition and adaptive aggregation [J]. Application Research of Computers, 2026, 43 (7). (2026-03-27). https://doi.org/10.19734/j.issn.1001-3695.2025.09.0440. )

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)