In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) has been redirecting to new domain since Jan. 1st, 2025.
See More
App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 1

Heterogeneity mitigation method based on knowledge distillation and inter-class relationship

He Yang
Peng Weimin
School of Computer Science & Technology, Hangzhou Dianzi University, Hangzhou 310000, China
DOI: 10.19734/j.issn.1001-3695.2025.05.0179

Abstract

Model heterogeneity stems from architectural differences among various clients, which hinders effective knowledge sharing in federated learning. Meanwhile, communication overhead arises from frequent parameter transmission during model updating, which restricts the scalability and efficiency of federated learning. To address these challenges, this paper proposed a federated learning framework called FedKIC based on knowledge distillation and inter-class relationship. FedKIC introduced a knowledge network to enable knowledge transfer between heterogeneous models through deep learning. It proposed an attention mechanism-based inter-class relationship learning strategy, which calculated the correlation between categories via cosine similarity and fused features to enhance the discriminability of similar categories. Additionally, it adopted a "class-level knowledge aggregation + shallow weight sharing" strategy to optimize communication efficiency. On the CIFAR10 and CIFAR100 datasets, compared with mainstream methods such as FedAvg and FedProx, FedKIC improved accuracy by 2.13%~3.48% and reduced communication overhead by 90%. Through inter-class relationship modeling and lightweight communication design, FedKIC breaks the "performance-efficiency-adaptability" trade-off in heterogeneous federated learning, providing a practical collaborative learning solution for distributed scenarios such as the Internet of Things and edge computing.

Foundation Support

浙江省科技计划项目(2023C01147)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.05.0179
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 1

Publish History

[2025-09-12] Accepted Paper

Cite This Article

何洋, 彭伟民. 基于知识蒸馏与类间关系的异构性缓解方法 [J]. 计算机应用研究, 2026, 43 (1). (2025-09-17). https://doi.org/10.19734/j.issn.1001-3695.2025.05.0179. (He Yang, Peng Weimin. Heterogeneity mitigation method based on knowledge distillation and inter-class relationship [J]. Application Research of Computers, 2026, 43 (1). (2025-09-17). https://doi.org/10.19734/j.issn.1001-3695.2025.05.0179. )

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)