Home > Research > Publications & Outputs > Resource Allocation for Latency-aware Federated...

Electronic data

  • FINAL VERSION

    Rights statement: ©2021 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

    Accepted author manuscript, 843 KB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Resource Allocation for Latency-aware Federated Learning in Industrial Internet-of-Things

Research output: Contribution to journalJournal articlepeer-review

E-pub ahead of print
  • W. Gao
  • Z. Zhao
  • G. Min
  • Q. Ni
  • Y. Jiang
Close
<mark>Journal publication date</mark>15/04/2021
<mark>Journal</mark>IEEE Transactions on Industrial Informatics
Number of pages9
Publication StatusE-pub ahead of print
Early online date15/04/21
<mark>Original language</mark>English

Abstract

Federated Learning (FL) has been employed for tremendous privacy-sensitive applications, where distributed devices collaboratively train a global model. In Industrial Internet-of-Things (IIoT) systems, training latency is the key performance metric as the automated manufacture usually requires timely processing. The existing works increase the number of effective devices to accelerate the training. However, devices in IIoT systems are usually densely deployed, increasing the number of clients can potentially cause serious interference and prolonged training latency. In this paper, we propose RaFed, a resource allocation scheme for FL. We formulate the problem of reducing training latency as an optimization problem, which is proved to be NP-hard. We propose a heuristic to select appropriate devices to achieve a good trade-off between the interference and convergence time. We conduct experiments using an RGB-D dataset in an IIoT system. The results show that compared to the state-of-the-art works, Rafed significantly reduces the latency by 29.9%.

Bibliographic note

©2021 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.