App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 10

Accuracy-driven adaptive federated pruning and differential privacy method

Yang Chenga
Li Xiaohuia
Lan Jieb
Wang Yajuna
a. School of Electronics & Information Engineering, b. College of Science, Liaoning University of Technology, Jinzhou Liaoning 121001, China
DOI: 10.19734/j.issn.1001-3695.2026.01.0054

Abstract

To address the high communication overhead caused by large model updates in federated learning, as well as the accuracy degradation and convergence fluctuation induced by differential privacy (DP) noise injection, this paper proposes an Accuracy-driven Adaptive Federated Pruning and Differential Privacy method (AAFDP) . On the server side, AAFDP constructs a performance feedback signal based on sliding average accuracy and adopts a staged “prune-then-perturb” workflow. Specifically, the method performs magnitude-based pruning on aggregated updates to form a sparse transmission structure, and injects Gaussian mechanism noise into the pruned updates during the DP stage. Meanwhile, the pruning ratio and noise multiplier are adaptively adjusted round by round according to the feedback signal. Experimental results on MNIST and CIFAR-10 show that, while maintaining high model accuracy and low loss, AAFDP reduces cumulative communication cost by about 33%–36% compared with dense transmission methods such as FedAvg, DP-FL, and APDP-FL. The proposed method achieves a favorable balance among model performance, training stability, and communication efficiency.

Foundation Support

国家自然科学基金资助项目(62203201)
辽宁省应用基础研究计划项目(2025JH2/101330118)
2024年辽宁省属本科高校基本科研业务费专项资金资助项目(LJZZ212410154025)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.01.0054
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 10

Publish History

[2026-07-29] Accepted Paper

Cite This Article

杨程, 李晓会, 兰洁, 等. 精度驱动的自适应联邦剪枝与差分隐私方法 [J]. 计算机应用研究, 2026, 43 (10). (2026-07-30). https://doi.org/10.19734/j.issn.1001-3695.2026.01.0054. (Yang Cheng, Li Xiaohui, Lan Jie, et al. Accuracy-driven adaptive federated pruning and differential privacy method [J]. Application Research of Computers, 2026, 43 (10). (2026-07-30). https://doi.org/10.19734/j.issn.1001-3695.2026.01.0054. )

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)