Federated Learning for Hybrid Beamforming in mm-Wave Massive MIMO

Basit Öğe Kaydı
dc.authoridColeri, Sinem/0000-0002-7502-3122
dc.authoridElbir, Ahmet M./0000-0003-4060-3781
dc.authorwosidColeri, Sinem/O-9829-2014
dc.authorwosidElbir, Ahmet M./X-3731-2019
dc.contributor.authorElbir, Ahmet M.
dc.contributor.authorColeri, Sinem
dc.date.accessioned2021-12-01T18:47:57Z
dc.date.available2021-12-01T18:47:57Z
dc.date.issued2020
dc.department[Belirlenecek]en_US
dc.description.abstractMachine learning for hybrid beamforming has been extensively studied by using centralized machine learning (CML) techniques, which require the training of a global model with a large dataset collected from the users. However, the transmission of the whole dataset between the users and the base station (BS) is computationally prohibitive due to limited communication bandwidth and privacy concerns. In this work, we introduce a federated learning (FL) based framework for hybrid beamforming, where the model training is performed at the BS by collecting only the gradients from the users. We design a convolutional neural network, in which the input is the channel data, yielding the analog beamformers at the output. Via numerical simulations, FL is demonstrated to be more tolerant to the imperfections and corruptions in the channel data as well as having less transmission overhead than CML.en_US
dc.description.sponsorshipScientific and Technological Research Council of TurkeyTurkiye Bilimsel ve Teknolojik Arastirma Kurumu (TUBITAK) [119E350]; Ford Otosanen_US
dc.description.sponsorshipSinem Coleri acknowledges the support of the Scientific and Technological Research Council of Turkey for EU CHISTERA grant 119E350 and Ford Otosan. The associate editor coordinating the review of this letter and approving it for publication was D. Ciuonzo.en_US
dc.identifier.doi10.1109/LCOMM.2020.3019312
dc.identifier.endpage2799en_US
dc.identifier.issn1089-7798
dc.identifier.issn1558-2558
dc.identifier.issue12en_US
dc.identifier.scopus2-s2.0-85097797840en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.startpage2795en_US
dc.identifier.urihttps://doi.org/10.1109/LCOMM.2020.3019312
dc.identifier.urihttps://hdl.handle.net/20.500.12684/10419
dc.identifier.volume24en_US
dc.identifier.wosWOS:000597750400030en_US
dc.identifier.wosqualityQ2en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherIeee-Inst Electrical Electronics Engineers Incen_US
dc.relation.ispartofIeee Communications Lettersen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectTrainingen_US
dc.subjectArray signal processingen_US
dc.subjectArtificial neural networksen_US
dc.subjectRadio frequencyen_US
dc.subjectMIMO communicationen_US
dc.subjectComputational modelingen_US
dc.subjectUnmanned aerial vehiclesen_US
dc.subjectDeep learningen_US
dc.subjectfederated learningen_US
dc.subjecthybrid beamformingen_US
dc.subjectmassive MIMOen_US
dc.subjectDesignen_US
dc.titleFederated Learning for Hybrid Beamforming in mm-Wave Massive MIMOen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
10419.pdf
Boyut:
529.16 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu