University of Oulu

X. Zhou, Y. Deng, H. Xia, S. Wu and M. Bennis, "Time-Triggered Federated Learning Over Wireless Networks," in IEEE Transactions on Wireless Communications, vol. 21, no. 12, pp. 11066-11079, Dec. 2022, doi: 10.1109/TWC.2022.3189601

Time-triggered federated learning over wireless networks

Saved in:
Author: Zhou, Xiaokang1; Deng, Yansha2; Xia, Huiyun1;
Organizations: 1School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150001, China
2Department of Engineering, King’s College London, London WC2R 2LS, U.K.
3Centre for Wireless Communications (CWC), University of Oulu, 90570 Oulu, Finland
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 4.8 MB)
Persistent link:
Language: English
Published: Institute of Electrical and Electronics Engineers, 2022
Publish Date: 2023-01-18


The newly emerging federated learning (FL) framework offers a new way to train machine learning models in a privacy-preserving manner. However, traditional FL algorithms are based on an event-triggered aggregation, which suffers from stragglers and communication overhead issues. To address these issues, in this paper, we present a time-triggered FL algorithm (TT-Fed) over wireless networks, which is a generalized form of classic synchronous and asynchronous FL. Taking the constrained resource and unreliable nature of wireless communication into account, we jointly study the user selection and bandwidth optimization problem to minimize the FL training loss. To solve this joint optimization problem, we provide a thorough convergence analysis for TT-Fed. Based on the obtained analytical convergence upper bound, the optimization problem is decomposed into tractable sub-problems with respect to each global aggregation round, and finally solved by our proposed online search algorithm. Simulation results show that compared to asynchronous FL (FedAsync) and FL with asynchronous user tiers (FedAT) benchmarks, our proposed TT-Fed algorithm improves the converged test accuracy by up to 12.5% and 5%, respectively, under highly imbalanced and non-IID data, while substantially reducing the communication overhead.

see all

Series: IEEE transactions on wireless communications
ISSN: 1536-1276
ISSN-E: 1558-2248
ISSN-L: 1536-1276
Volume: 21
Issue: 12
Pages: 11066 - 11079
DOI: 10.1109/TWC.2022.3189601
Type of Publication: A1 Journal article – refereed
Field of Science: 213 Electronic, automation and communications engineering, electronics
Funding: This work was supported in part by the Natural Science Foundation of China under Grant 61671173, Grant 62171163, and Grant 61831002; and in part by the Engineering and Physical Sciences Research Council (EPSRC), U.K., under Grant EP/W004348/1. The work of Xiaokang Zhou was supported by the China Scholarship Council, and was performed during his visit at King’s College London.
Copyright information: © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.