In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) will be discontinued after Dec. 31st, 2024.
See More
Algorithm Research & Explore
|
App. Res. of Comp. Printed Article
Vol. 41, 2024 No. 8
2419-2426

Decentralized privacy-preserving optimization method for federated learning

Hou Zechao
Dong Jiangang
College of Software, Xinjiang University, rümqi 830000, China
DOI: 10.19734/j.issn.1001-3695.2023.12.0611

Abstract

The advent of federated learning has unveiled a collaborative approach to learning across data islands, yet its scalability faces challenges from Non-IID local data at federated nodes and insufficient oversight, accountability, and privacy in centralized frameworks. To tackle these issues, this paper proposed a blockchain-based trustworthy slice aggregation(BBTSA) and federated attribution optimization method(FedAom). FedAom adopted attribution thinking, using the integrated gradients method for attribution to identify parameters influencing model decisions. It considered parameter sensitivity in a tiered app-roach, preserving and enhancing key knowledge learned by the global model during local updates. This effectively utilized shared data to mitigate the Non-IID problem. Concurrently, BBTSA employed blockchain to establish a decentralized framework, facilitating noise exchange between nodes instead of direct parameters, with a cooperative tree structure for obfuscation to boost privacy. Validation on diverse distributions across two datasets indicates FedAom notably improves stability and convergence speed over baseline methods in most instances. Simultaneously, BBTSA ensures client privacy without compromising model accuracy, guaranteeing training oversight and privacy protection.

Publish Information

DOI: 10.19734/j.issn.1001-3695.2023.12.0611
Publish at: Application Research of Computers Printed Article, Vol. 41, 2024 No. 8
Section: Algorithm Research & Explore
Pages: 2419-2426
Serial Number: 1001-3695(2024)08-024-2419-08

Publish History

[2024-03-07] Accepted Paper
[2024-08-05] Printed Article

Cite This Article

侯泽超, 董建刚. 去中心化场景下的隐私保护联邦学习优化方法 [J]. 计算机应用研究, 2024, 41 (8): 2419-2426. (Hou Zechao, Dong Jiangang. Decentralized privacy-preserving optimization method for federated learning [J]. Application Research of Computers, 2024, 41 (8): 2419-2426. )

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)