Asynchronous Federated Learning via Over-the-Air Computation

Zijian Zheng*, Yansha Deng, Xiaonan Liu*, Arumugam Nallanathan*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

Abstract

The emerging field of federated learning (FL) provides great potential for edge intelligence while protecting data privacy. However, as the system grows in scale or becomes more heterogeneous, new challenges, such as the spectrum shortage and stragglers issues, arise. These issues can potentially be addressed by over-the-air computation (AirComp) and asynchronous FL, respectively, however, their combination is difficult due to their conflicting requirements. In this paper, we propose a novel asynchronous FL with AirComp in a time-triggered manner (async-AirFed). The conventional async aggregation requests the historical data to be used for model updates, which can cause the accumulation of channel noise and interference when AirComp is applied. To address this issue, we propose a simple but effective truncation method which retains a limited length of historical data. Convergence analysis presents that our proposed async-AirFed converges on non-convex optimality function with sub-linear rate. Simulation results show that our proposed scheme achieves more than 34% faster convergence than the benchmarks, by achieving an accuracy of 85%, which also improves the time utilization efficiency and reduces the impact of staleness and the channel.

Original languageEnglish
Title of host publicationGLOBECOM 2023 - 2023 IEEE Global Communications Conference
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1345-1350
Number of pages6
ISBN (Electronic)9798350310900
DOIs
Publication statusPublished - 2023
Event2023 IEEE Global Communications Conference, GLOBECOM 2023 - Kuala Lumpur, Malaysia
Duration: 4 Dec 20238 Dec 2023

Publication series

NameProceedings - IEEE Global Communications Conference, GLOBECOM
ISSN (Print)2334-0983
ISSN (Electronic)2576-6813

Conference

Conference2023 IEEE Global Communications Conference, GLOBECOM 2023
Country/TerritoryMalaysia
CityKuala Lumpur
Period4/12/20238/12/2023

Keywords

  • Asynchronous federated learning
  • error accumulation
  • over-the-air computation

Fingerprint

Dive into the research topics of 'Asynchronous Federated Learning via Over-the-Air Computation'. Together they form a unique fingerprint.

Cite this