Publications

Detailed Information

Personalized Federated Learning With Server-Side Information

DC Field Value Language
dc.contributor.authorSong, Jaehun-
dc.contributor.authorOh, Min-Hwan-
dc.contributor.authorKim, Hyung-Sin-
dc.date.accessioned2024-05-14T08:06:11Z-
dc.date.available2024-05-14T08:06:11Z-
dc.date.created2023-01-04-
dc.date.issued2022-11-
dc.identifier.citationIEEE Access, Vol.10, pp.120245-120255-
dc.identifier.issn2169-3536-
dc.identifier.urihttps://hdl.handle.net/10371/202134-
dc.description.abstractPersonalized Federated Learning (FL) is an emerging research field in FL that learns an easily adaptable global model in the presence of data heterogeneity among clients. However, one of the main challenges for personalized FL is the heavy reliance on clients' computing resources to calculate higher-order gradients since client data is segregated from the server to ensure privacy. To resolve this, we focus on a problem setting where the server may possess data independent of clients' data - a prevalent problem setting in various applications, yet relatively unexplored in the existing literature. Specifically, we propose FedSIM, a new method for personalized FL that actively utilizes such server data to improve meta-gradient calculation in the server for increased personalization performance. Experimentally, we demonstrate through various benchmarks and ablations that FedSIM is superior to existing methods in terms of accuracy, more computationally efficient by calculating the full meta-gradients in the server, and converges up to 34.2% faster.-
dc.language영어-
dc.publisherInstitute of Electrical and Electronics Engineers Inc.-
dc.titlePersonalized Federated Learning With Server-Side Information-
dc.typeArticle-
dc.identifier.doi10.1109/ACCESS.2022.3221401-
dc.citation.journaltitleIEEE Access-
dc.identifier.wosid000890180300001-
dc.identifier.scopusid2-s2.0-85141647474-
dc.citation.endpage120255-
dc.citation.startpage120245-
dc.citation.volume10-
dc.description.isOpenAccessY-
dc.contributor.affiliatedAuthorOh, Min-Hwan-
dc.contributor.affiliatedAuthorKim, Hyung-Sin-
dc.type.docTypeArticle-
dc.description.journalClass1-
dc.subject.keywordAuthorServers-
dc.subject.keywordAuthorData models-
dc.subject.keywordAuthorComputational modeling-
dc.subject.keywordAuthorAdaptation models-
dc.subject.keywordAuthorFederated learning-
dc.subject.keywordAuthorTask analysis-
dc.subject.keywordAuthorPredictive models-
dc.subject.keywordAuthorMetasearch-
dc.subject.keywordAuthorpersonalization-
dc.subject.keywordAuthormeta-learning-
Appears in Collections:
Files in This Item:
There are no files associated with this item.

Related Researcher

  • Graduate School of Data Science
Research Area Distributed machine learning, Edge, Mobile AI

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share