Decentralized Federated Learning: A Survey and Perspective

Liangqi Yuan, Ziran Wang, Lichao Sun, Philip S. Yu, Christopher G. Brinton

Research output: Contribution to journalArticlepeer-review

18 Scopus citations

Abstract

Federated learning (FL) has been gaining attention for its ability to share knowledge while maintaining user data, protecting privacy, increasing learning efficiency, and reducing communication overhead. Decentralized FL (DFL) is a decentralized network architecture that eliminates the need for a central server in contrast to centralized FL (CFL). DFL enables direct communication between clients, resulting in significant savings in communication resources. In this article, a comprehensive survey and profound perspective are provided for DFL. First, a review of the methodology, challenges, and variants of CFL is conducted, laying the background of DFL. Then, a systematic and detailed perspective on DFL is introduced, including iteration order, communication protocols, network topologies, paradigm proposals, and temporal variability. Next, based on the definition of DFL, several extended variants and categorizations are proposed with state-of-the-art (SOTA) technologies. Lastly, in addition to summarizing the current challenges in the DFL, some possible solutions and future research directions are also discussed.

Original languageEnglish (US)
Pages (from-to)34617-34638
Number of pages22
JournalIEEE Internet of Things Journal
Volume11
Issue number21
DOIs
StatePublished - 2024
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Information Systems
  • Hardware and Architecture
  • Computer Science Applications
  • Computer Networks and Communications

Keywords

  • Decentralized learning
  • Internet of Things (IoT)
  • federated learning (FL)
  • network
  • privacy preservation

Fingerprint

Dive into the research topics of 'Decentralized Federated Learning: A Survey and Perspective'. Together they form a unique fingerprint.

Cite this