Please use this identifier to cite or link to this item: http://bura.brunel.ac.uk/handle/2438/27795
Full metadata record
DC FieldValueLanguage
dc.contributor.authorYan, N-
dc.contributor.authorWang, K-
dc.contributor.authorPan, C-
dc.contributor.authorChai, KK-
dc.contributor.authorShu, F-
dc.contributor.authorWang, J-
dc.date.accessioned2023-12-03T13:57:15Z-
dc.date.available2023-12-03T13:57:15Z-
dc.date.issued2023-12-01-
dc.identifierORCID iD: Na Yan https://orcid.org/0000-0003-1388-8566-
dc.identifierORCID iD: Kezhi Wang https://orcid.org/0000-0001-8602-0800-
dc.identifierORCID iD: Cunhua Pan https://orcid.org/0000-0001-5286-7958-
dc.identifierORCID iD: Feng Shu https://orcid.org/0000-0003-0073-1965-
dc.identifierORCID iD: Jiangzhou Wang https://orcid.org/0000-0003-0881-3594-
dc.identifier.citationYan, N. et al. (2023) 'Over-the-Air Federated Averaging with Limited Power and Privacy Budgets', IEEE Transactions on Communications, 0 (early access), pp. 1 - 16. doi: 10.1109/tcomm.2023.3338738.en_US
dc.identifier.issn0090-6778-
dc.identifier.urihttps://bura.brunel.ac.uk/handle/2438/27795-
dc.descriptionPart of this work will be presented in IEEE International Conference on Communications (ICC), 28 May – 01 June 2023, Rome, Italy.-
dc.description.abstractThis paper develops an optimal design for device scheduling, alignment coefficient, and aggregation rounds within a differentially private over-the-air federated averaging (DP-OTA-FedAvg) system considering a constrained sum power budget. In DP-OTA-FedAvg, gradients are aligned using an alignment coefficient and then aggregated over the air, utilizing channel noise to ensure participant privacy. This study highlights two critical tradeoffs in aligned over-the-air federated learning (OTA-FL) systems with limited power and privacy budgets. Firstly, it reveals the tradeoff between the number of scheduled devices and the alignment coefficient. Secondly, it investigates the balance between aggregation distortion and local training error while adhering to the sum power constraint. Specifically, we measure privacy using differential privacy (DP) and perform convergence analyses for both convex and non-convex loss functions. These analyses provide insights into how device scheduling, the alignment coefficient, and the number of global aggregations affect both privacy preservation and the learning process. Building on these analytical results, we formulate an optimization problem aimed at minimizing the optimality gap of DP-OTA-FedAvg under power and privacy constraints. By specifying the number of aggregation rounds, we derive a closed-form expression describing the relationship between the alignment coefficient and the number of scheduled devices. We then tackle the problem through iterative optimization of scheduling and aggregation rounds. The effectiveness of the proposed policies is verified through simulations, and the performance advantage is particularly pronounced in scenarios where devices have poor channel conditions and limited sum-power budgets.en_US
dc.format.extent1 - 16-
dc.format.mediumPrint-Electronic-
dc.language.isoen_USen_US
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.rightsCopyright © 2023 Institute of Electrical and Electronics Engineers (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. See: https://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelines-and-policies/post-publication-policies/-
dc.rights.urihttps://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelines-and-policies/post-publication-policies/-
dc.subjectfederated averagingen_US
dc.subjectdifferential privacyen_US
dc.subjectdevice schedulingen_US
dc.subjectsum-power constrainten_US
dc.titleOver-the-Air Federated Averaging with Limited Power and Privacy Budgetsen_US
dc.typeArticleen_US
dc.identifier.doihttps://doi.org/10.1109/tcomm.2023.3338738-
dc.relation.isPartOfIEEE Transactions on Communications-
pubs.publication-statusPublished-
pubs.volume0-
dc.identifier.eissn1558-0857-
dc.rights.holderInstitute of Electrical and Electronics Engineers (IEEE)-
Appears in Collections:Dept of Computer Science Research Papers

Files in This Item:
File Description SizeFormat 
FullText.pdfCopyright © 2023 Institute of Electrical and Electronics Engineers (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. See: https://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelines-and-policies/post-publication-policies/3.74 MBAdobe PDFView/Open


Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.