App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 5

Heterogeneous federated learning with personalized auxiliary network and output stacking

Zeng Qinglong
Cao Dongtao
Yan Liangqi
Zhang Jiale
Chen Zheyi
Cheng Hongju
College of Computer and Data Science, Fuzhou University, Fuzhou 350108, China
DOI: 10.19734/j.issn.1001-3695.2025.09.0372

Abstract

Federated learning is a distributed machine learning paradigm in which a central server coordinates the training of multiple clients on data dispersed across different devices. It is generally assumed that the models on the server and all clients have an identical structure, and thus the server can aggregate these shared parameters of the clients to improve the performance of the global model. However, the hardware of clients varies from each other in the real-world scenarios, and it is expected to design unique model structures for the clients. In order to achieve collaborative training among clients in scenarios with model heterogeneity, this paper proposed a novel heterogeneous Federated learning with Personalized Auxiliary network and output Stacking (FedPAS) . First, the server deployed an auxiliary network to assist each client in coordinating with itself. By integrating gradient-based representations of data from different clients into the auxiliary network’s loss function, the auxiliary network underwent personalization and was sent to the clients. Second, inspired by multiple model output concatenation methods in ensemble learning, this work proposed an output stacking strategy to acquire the local data representations through the auxiliary network of the client. The server aggregated these representations to generate metadata to train the clients’ model. Finally, experimental results with diverse data distributions on MNIST and CIFAR10 datasets demonstrate that this method surpasses several recent federated learning methods addressing model heterogeneity in prediction accuracy while exhibiting stronger generalization capabilities.

Foundation Support

国家自然科学基金资助项目(62372111)
福建省自然科学基金资助项目(2023J01267)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.09.0372
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 5

Publish History

[2026-01-13] Accepted Paper

Cite This Article

曾庆泷, 曹栋涛, 颜良棋, 等. 基于个性化辅助网络和输出堆叠的异构联邦学习方法 [J]. 计算机应用研究, 2026, 43 (5). (2026-01-20). https://doi.org/10.19734/j.issn.1001-3695.2025.09.0372. (Zeng Qinglong, Cao Dongtao, Yan Liangqi, et al. Heterogeneous federated learning with personalized auxiliary network and output stacking [J]. Application Research of Computers, 2026, 43 (5). (2026-01-20). https://doi.org/10.19734/j.issn.1001-3695.2025.09.0372. )

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)