OFDMA-F<sup>2</sup>L: Federated Learning with Flexible Aggregation over an OFDMA Air Interface

Hu, S; Yuan, X; Ni, W; Wang, X; Hossain, E; Vincent Poor, H

OFDMA-F<sup>2</sup>L: Federated Learning with Flexible Aggregation over an OFDMA Air Interface

Hu, S Yuan, X

Ni, W

Wang, X Hossain, E Vincent Poor, H

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE Transactions on Wireless Communications, 2024, 23, (7), pp. 6793-6807
Issue Date:: 2024-01-01

Closed Access

	Filename	Description	Size
	1694541.pdf	Published version	9.16 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Hu, S
dc.contributor.author	Yuan, X https://orcid.org/0000-0002-9167-1613
dc.contributor.author	Ni, W https://orcid.org/0000-0002-4933-594X
dc.contributor.author	Wang, X
dc.contributor.author	Hossain, E
dc.contributor.author	Vincent Poor, H
dc.date.accessioned	2024-08-07T04:38:28Z
dc.date.available	2024-08-07T04:38:28Z
dc.date.issued	2024-01-01
dc.identifier.citation	IEEE Transactions on Wireless Communications, 2024, 23, (7), pp. 6793-6807
dc.identifier.issn	1536-1276
dc.identifier.issn	1558-2248
dc.identifier.uri	http://hdl.handle.net/10453/180213
dc.description.abstract	Federated learning (FL) can suffer from communication bottlenecks when deployed in mobile networks, limiting participating clients and deterring FL convergence. In this context, the impact of practical air interfaces with discrete modulation schemes on FL has not previously been studied in depth. This paper proposes a new paradigm of flexible aggregation-based FL (F2L ) over an orthogonal frequency division multiple-access (OFDMA) air interface, termed as 'OFDMA-F2L ', allowing selected clients to train local models for various numbers of iterations before uploading the models in each aggregation round. We optimize the selections of clients, subchannels and modulation scheme, adapting to channel conditions and computing power. Specifically, we derive an upper bound on the optimality gap of OFDMA-F2L capturing the impact of these selections, and show that the upper bound is minimized by maximizing the weighted sum rate of the clients per aggregation round. A Lagrange-dual based method is developed to solve this challenging mixed integer program of weighted sum rate maximization, revealing that a 'winner-takes-all' policy provides the almost surely optimal client, subchannel, and modulation selections. Experiments on multilayer perceptrons and convolutional neural networks show that OFDMA-F2L with optimal selections can significantly improve the training convergence and accuracy, e.g., by about 18% and 5%, compared to potential alternatives.
dc.language	English
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation.ispartof	IEEE Transactions on Wireless Communications
dc.relation.isbasedon	10.1109/TWC.2023.3334691
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0805 Distributed Computing, 0906 Electrical and Electronic Engineering, 1005 Communications Technologies
dc.subject.classification	Networking & Telecommunications
dc.subject.classification	4006 Communications engineering
dc.subject.classification	4008 Electrical engineering
dc.subject.classification	4606 Distributed computing and systems software
dc.title	OFDMA-F<sup>2</sup>L: Federated Learning with Flexible Aggregation over an OFDMA Air Interface
dc.type	Journal Article
utslib.citation.volume	23
utslib.for	0805 Distributed Computing
utslib.for	0906 Electrical and Electronic Engineering
utslib.for	1005 Communications Technologies
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
utslib.copyright.status	closed_access	*
dc.date.updated	2024-08-07T04:38:19Z
pubs.issue	7
pubs.publication-status	Published
pubs.volume	23
utslib.citation.issue	7

Abstract:

Federated learning (FL) can suffer from communication bottlenecks when deployed in mobile networks, limiting participating clients and deterring FL convergence. In this context, the impact of practical air interfaces with discrete modulation schemes on FL has not previously been studied in depth. This paper proposes a new paradigm of flexible aggregation-based FL (F2L ) over an orthogonal frequency division multiple-access (OFDMA) air interface, termed as 'OFDMA-F2L ', allowing selected clients to train local models for various numbers of iterations before uploading the models in each aggregation round. We optimize the selections of clients, subchannels and modulation scheme, adapting to channel conditions and computing power. Specifically, we derive an upper bound on the optimality gap of OFDMA-F2L capturing the impact of these selections, and show that the upper bound is minimized by maximizing the weighted sum rate of the clients per aggregation round. A Lagrange-dual based method is developed to solve this challenging mixed integer program of weighted sum rate maximization, revealing that a 'winner-takes-all' policy provides the almost surely optimal client, subchannel, and modulation selections. Experiments on multilayer perceptrons and convolutional neural networks show that OFDMA-F2L with optimal selections can significantly improve the training convergence and accuracy, e.g., by about 18% and 5%, compared to potential alternatives.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/180213