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

Adaptive privacy budget allocation for non-iid federated learning: research status and challenges

He Lili
Li Jinhong
Zhang Lei
Pan Chang
Guan Xinru
Yan Wengang
School of Information and Electronic Technology, Jiamusi University, Jiamusi Heilongjiang 154007, China
DOI: 10.19734/j.issn.1001-3695.2025.12.0539

Abstract

Addressing the failure of traditional fixed privacy budget allocation in Non-IID Federated Learning (FL) due to significant variations in gradient sensitivity, this paper systematically reviews the methods and technical progress of adaptive privacy budget allocation (PBA) . As a core tool for balancing privacy strength and model utility in distributed systems, adaptive privacy budget allocation strategies play a vital role in resolving gradient distortion and model convergence difficulties. This study first establishes a classification framework encompassing three mainstream approaches: statistical metrics, learning algorithms, and rule-based games. It then provides an in-depth analysis of statistical quantification mechanisms based on Kullback-Leibler (KL) divergence and Wasserstein distance, explores the decision-optimization mechanisms of reinforcement learning (RL) and meta-learning in complex environments, and discusses the coordination logic of threshold rules, Nash Equilibrium, and incentive mechanisms. Finally, the paper summarizes the challenges in quantitative measurement, computational overhead, and system fairness, while forecasting future trends such as automated differential privacy (Auto-DP) and privacy-preserving fine-tuning for large language models (LLMs) , thus providing a theoretical foundation for building efficient and robust distributed privacy security systems.

Foundation Support

黑龙江省自然科学基金联合基金培育项目(PL2024F002)
黑龙江省省属本科高校优秀青年教师基础研究支持计划(YQJH2024239)
黑龙江省省属高等学校基本科研业务费优秀创新团队建设项目(2022-KYYWF-0654)
佳木斯大学"东极"学术团队(DJXSTD202417)
黑龙江省自主智能与信息处理重点实验室开放课题(ZZXC202302)
佳木斯大学博士专项科研启动项目(项目编号:JMSUBZ2024-07)
佳木斯市科技计划创新激励类项目(GY2025JL0004)
国家外国专家重点支持项目(D20250185)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2025.12.0539
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 10

Publish History

[2026-07-03] Accepted Paper

Cite This Article

何丽丽, 李金红, 张磊, 等. 面向Non-IID联邦学习的自适应隐私预算分配：研究现状与挑战 [J]. 计算机应用研究, 2026, 43 (10). (2026-07-30). https://doi.org/10.19734/j.issn.1001-3695.2025.12.0539. (He Lili, Li Jinhong, Zhang Lei, et al. Adaptive privacy budget allocation for non-iid federated learning: research status and challenges [J]. Application Research of Computers, 2026, 43 (10). (2026-07-30). https://doi.org/10.19734/j.issn.1001-3695.2025.12.0539. )

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)