App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 6

Heterogeneous federated learning based on cross-correlation collaboration and contrastive distillation

Xu Yifan1
Liu Wenxin1
Ye Weidu2
Ye Ning1
1. School of Information Science and Artificial Intelligence, Nanjing Forestry University, Nanjing Jiangsu 210037, China
2. School of Computer Science and Engineering, School of Software, and School of Cyberspace Security, Nanjing University of Posts and Telecommunications, Nanjing Jiangsu 210023, China
DOI: 10.19734/j.issn.1001-3695.2025.09.0413

Abstract

To address collaborative difficulties caused by model heterogeneity and performance degradation from local data noise, this paper proposed a Robust Contrastive Cross-Correlation Federated Learning (CCFL) algorithm. The algorithm introduced a cross-correlation matrix and utilized unlabeled public data for information communication among clients. This approach achieved heterogeneous collaborative learning. Furthermore, the method applied adversarial perturbations to enhance learning stability. Locally, the algorithm optimized the self-learning module through momentum distillation, contrastive learning, and Generalized Cross-Entropy loss. These techniques mitigated the impact of noisy labels. Experimental results on MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100 datasets showed that CCFL improved accuracy by an average of 7.95% compared to mainstream methods. The results indicate that the proposed method effectively enhances model robustness and generalization capabilities in heterogeneous environments.

Foundation Support

国家青年科学基金项目(62502228)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.09.0413
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 6

Publish History

[2026-02-25] Accepted Paper

Cite This Article

徐一帆, 刘文欣, 业苇渡, 等. 基于互相关协作和对比蒸馏的异构联邦学习 [J]. 计算机应用研究, 2026, 43 (6). (2026-02-25). https://doi.org/10.19734/j.issn.1001-3695.2025.09.0413. (Xu Yifan, Liu Wenxin, Ye Weidu, et al. Heterogeneous federated learning based on cross-correlation collaboration and contrastive distillation [J]. Application Research of Computers, 2026, 43 (6). (2026-02-25). https://doi.org/10.19734/j.issn.1001-3695.2025.09.0413. )

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)