OFedIT: Communication-Efficient Online Federated Learning with Intermittent Transmission
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kwon, Dohyeok | - |
dc.contributor.author | Park, Jonghwan | - |
dc.contributor.author | Hong, Songnam | - |
dc.date.accessioned | 2023-01-25T10:09:20Z | - |
dc.date.available | 2023-01-25T10:09:20Z | - |
dc.date.created | 2023-01-05 | - |
dc.date.issued | 2022-10 | - |
dc.identifier.issn | 2162-1233 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/182237 | - |
dc.description.abstract | We study an online federated learning (OFL) where many edge nodes receive their own data sequentially and train a sequence of global functions (or models) under the orchestration of a central server while keeping data localized. In this framework, finding a communication-efficient algorithm is one of the challenges for online federated learning (OFL). We present a communication-efficient OFL algorithm (named OFedIT) using intermittent transmissions. Our main contribution is to theoretically prove that OFedIT over T time slots achieves an optimal sublinear regret bound mathcal{O}( sqrt{T}). Furthermore, this asymptotic optimality is ensured even when data- and system-heterogeneity are taken into account. Our analysis reveals that OFedIT yields the almost same performance as the centralized counterpart (i.e., all local data are gathered at the server) while having the advantages of communication cost and data-privacy. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | IEEE Computer Society | - |
dc.title | OFedIT: Communication-Efficient Online Federated Learning with Intermittent Transmission | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Hong, Songnam | - |
dc.identifier.doi | 10.1109/ICTC55196.2022.9952884 | - |
dc.identifier.scopusid | 2-s2.0-85143256010 | - |
dc.identifier.bibliographicCitation | International Conference on ICT Convergence, v.2022-October, pp.1189 - 1192 | - |
dc.relation.isPartOf | International Conference on ICT Convergence | - |
dc.citation.title | International Conference on ICT Convergence | - |
dc.citation.volume | 2022-October | - |
dc.citation.startPage | 1189 | - |
dc.citation.endPage | 1192 | - |
dc.type.rims | ART | - |
dc.type.docType | Conference Paper | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | N | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordPlus | E-learning | - |
dc.subject.keywordPlus | Data privacy | - |
dc.subject.keywordPlus | Central servers | - |
dc.subject.keywordPlus | Edge nodes | - |
dc.subject.keywordPlus | Federated learning | - |
dc.subject.keywordPlus | Global functions | - |
dc.subject.keywordPlus | Global models | - |
dc.subject.keywordPlus | Intermittent transmission | - |
dc.subject.keywordPlus | Localised | - |
dc.subject.keywordPlus | Online learning | - |
dc.subject.keywordPlus | Regret analyse | - |
dc.subject.keywordPlus | Timeslots | - |
dc.subject.keywordAuthor | Federated learning | - |
dc.subject.keywordAuthor | Online learning | - |
dc.subject.keywordAuthor | Regret analysis | - |
dc.identifier.url | https://ieeexplore.ieee.org/document/9952884 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.