Asynchronous Online Federated Learning with Reduced Communication Requirements

Francois Gauthier, Vinay Chakravarthi Gogineni*, Stefan Werner, Yih Fang Huang, Anthony Kuh

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

33 Downloads (Pure)

Abstract

Online federated learning (FL) enables geographically distributed devices to learn a global shared model from locally available streaming data. Most online FL literature considers a best case scenario regarding the participating clients and the communication channels. However, these assumptions are often not met in real-world applications. Asynchronous settings can reflect a more realistic environment, such as heterogeneous client participation due to available computational power and battery constraints, as well as delays caused by communication channels or straggler devices. Further, in most applications, energy efficiency must be taken into consideration. Using the principles of partial-sharing-based communications, we propose a communication-efficient asynchronous online FL (PAO-Fed) strategy. By reducing the communication load of the participants, the proposed method renders participation more accessible and efficient. In addition, the proposed aggregation mechanism accounts for random participation, handles delayed updates, and mitigates their effect on accuracy. We study the first- and second-order convergence of the proposed PAO-Fed method and obtain an expression for its steady-state mean square deviation. Finally, we conduct comprehensive simulations to study the performance of the proposed method on both synthetic and real-life data sets. The simulations reveal that in asynchronous settings, the proposed PAO-Fed is able to achieve the same convergence properties as that of the online federated stochastic gradient while reducing the communication by 98%.

Original languageEnglish
JournalIEEE Internet of Things Journal
Volume10
Issue number23
Pages (from-to)20761-20775
ISSN2327-4662
DOIs
Publication statusPublished - 1. Dec 2023

Keywords

  • Asynchronous behavior
  • communication efficiency
  • Computational modeling
  • Convergence
  • Data models
  • Delays
  • Federated learning
  • Load modeling
  • nonlinear regression
  • online federated learning
  • partial-sharing-based communications
  • Servers
  • online federated learning (FL)

Fingerprint

Dive into the research topics of 'Asynchronous Online Federated Learning with Reduced Communication Requirements'. Together they form a unique fingerprint.

Cite this