Open Access System for Information Sharing

Login Library

 

Article
Cited 5 time in webofscience Cited 5 time in scopus
Metadata Downloads
Full metadata record
Files in This Item:
There are no files associated with this item.
DC FieldValueLanguage
dc.contributor.authorYONGJEONG, OH-
dc.contributor.authorJEON, YO SEB-
dc.contributor.authorChen, Mingzhe-
dc.contributor.authorSaad, Walid-
dc.date.accessioned2023-09-01T07:20:28Z-
dc.date.available2023-09-01T07:20:28Z-
dc.date.created2023-07-21-
dc.date.issued2024-03-
dc.identifier.issn1536-1276-
dc.identifier.urihttps://oasis.postech.ac.kr/handle/2014.oak/118502-
dc.description.abstractIn this paper, a new communication-efficient federated learning (FL) framework is proposed, inspired by vector quantized compressed sensing. The basic strategy of the proposed framework is to compress the local model update at each device by applying dimensionality reduction followed by vector quantization. Subsequently, the global model update is reconstructed at a parameter server by applying a sparse signal recovery algorithm to the aggregation of the compressed local model updates. By harnessing the benefits of both dimensionality reduction and vector quantization, the proposed framework effectively reduces the communication overhead of local update transmissions. Both the design of the vector quantizer and the key parameters for the compression are optimized so as to minimize the reconstruction error of the global model update under the constraint of wireless link capacity. By considering the reconstruction error, the convergence rate of the proposed framework is also analyzed for a non-convex loss function. Simulation results on the MNIST and FEMNIST datasets demonstrate that the proposed framework provides more than a 2.4% increase in classification accuracy compared to state-of-the-art FL frameworks when the communication overhead of the local model update transmission is 0.1 bit per local model entry.-
dc.languageEnglish-
dc.publisherInstitute of Electrical and Electronics Engineers-
dc.relation.isPartOfIEEE Transactions on Wireless Communications-
dc.titleFedVQCS: Federated Learning via Vector Quantized Compressed Sensing-
dc.typeArticle-
dc.identifier.doi10.1109/twc.2023.3291877-
dc.type.rimsART-
dc.identifier.bibliographicCitationIEEE Transactions on Wireless Communications, v.23, no.3, pp.1 - 1-
dc.identifier.wosid001196528600048-
dc.citation.endPage1-
dc.citation.number3-
dc.citation.startPage1-
dc.citation.titleIEEE Transactions on Wireless Communications-
dc.citation.volume23-
dc.contributor.affiliatedAuthorYONGJEONG, OH-
dc.contributor.affiliatedAuthorJEON, YO SEB-
dc.identifier.scopusid2-s2.0-85164683558-
dc.description.journalClass1-
dc.description.journalClass1-
dc.description.isOpenAccessN-
dc.type.docTypeArticle-
dc.subject.keywordAuthordimensionality reduction-
dc.subject.keywordAuthordistributed learning-
dc.subject.keywordAuthorFederated learning-
dc.subject.keywordAuthorquantized compressed sensing-
dc.subject.keywordAuthorvector quantization-
dc.relation.journalWebOfScienceCategoryEngineering, Electrical & Electronic-
dc.relation.journalWebOfScienceCategoryTelecommunications-
dc.description.journalRegisteredClassscie-
dc.description.journalRegisteredClassscopus-
dc.relation.journalResearchAreaEngineering-
dc.relation.journalResearchAreaTelecommunications-

qr_code

  • mendeley

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

Related Researcher

Researcher

전요셉JEON, YO SEB
Dept of Electrical Enginrg
Read more

Views & Downloads

Browse