Federated learning for client-specific neural network parameter generation for wireless communication

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a client may determine, using a conditioning network and based at least in part on an observed environmental vector, a set of client-specific parameters. The client may determine a latent vector us...

Full description

Saved in:
Bibliographic Details
Main Authors Bhushan, Naga, Yoo, Taesang, Sundararajan, Jay Kumar, Mukkavilli, Krishna Kiran, Kwon, Hwan Joon, Namgoong, June, Ji, Tingfang, Vitthaladevuni, Pavan Kumar
Format Patent
LanguageEnglish
Published 20.02.2024
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC COMMUNICATION TECHNIQUE
ELECTRICITY
PHYSICS
TRANSMISSION
Online AccessGet full text

Cover

Abstract Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a client may determine, using a conditioning network and based at least in part on an observed environmental vector, a set of client-specific parameters. The client may determine a latent vector using a client autoencoder and based at least in part on the set of client-specific parameters and the set of shared parameters. The client may transmit the observed environmental vector and the latent vector to a server. Numerous other aspects are provided.
AbstractList Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a client may determine, using a conditioning network and based at least in part on an observed environmental vector, a set of client-specific parameters. The client may determine a latent vector using a client autoencoder and based at least in part on the set of client-specific parameters and the set of shared parameters. The client may transmit the observed environmental vector and the latent vector to a server. Numerous other aspects are provided.
Author Ji, Tingfang
Yoo, Taesang
Vitthaladevuni, Pavan Kumar
Bhushan, Naga
Sundararajan, Jay Kumar
Kwon, Hwan Joon
Mukkavilli, Krishna Kiran
Namgoong, June
Author_xml – fullname: Bhushan, Naga
– fullname: Yoo, Taesang
– fullname: Sundararajan, Jay Kumar
– fullname: Mukkavilli, Krishna Kiran
– fullname: Kwon, Hwan Joon
– fullname: Namgoong, June
– fullname: Ji, Tingfang
– fullname: Vitthaladevuni, Pavan Kumar
BookMark eNqNjDsOwjAQBV1Awe8O5gCRSKAgLYiIHqijlfMSWThra-0o1ydEHIBqinnz1mrBnrFSqNBAKKHRDiRsudOtF22cBacsBhjbWqMZg5CbkEYvbx1IqEeC6A787a3nuRutwCFGbXzfD2zNrLZq2ZKL2P24Ufvq9rzeMwRfIwYy00uqX488Lw_l6VxciuM_mw_86UI4
ContentType Patent
DBID EVB
DatabaseName esp@cenet
DatabaseTitleList
Database_xml – sequence: 1
  dbid: EVB
  name: esp@cenet
  url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP
  sourceTypes: Open Access Repository
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
Chemistry
Sciences
Physics
ExternalDocumentID US11909482B2
GroupedDBID EVB
ID FETCH-epo_espacenet_US11909482B23
IEDL.DBID EVB
IngestDate Fri Jul 19 12:56:56 EDT 2024
IsOpenAccess true
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-epo_espacenet_US11909482B23
Notes Application Number: US202117444028
OpenAccessLink https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240220&DB=EPODOC&CC=US&NR=11909482B2
ParticipantIDs epo_espacenet_US11909482B2
PublicationCentury 2000
PublicationDate 20240220
PublicationDateYYYYMMDD 2024-02-20
PublicationDate_xml – month: 02
  year: 2024
  text: 20240220
  day: 20
PublicationDecade 2020
PublicationYear 2024
RelatedCompanies QUALCOMM Incorporated
RelatedCompanies_xml – name: QUALCOMM Incorporated
Score 3.5245457
Snippet Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a client may determine, using a conditioning network and...
SourceID epo
SourceType Open Access Repository
SubjectTerms CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC COMMUNICATION TECHNIQUE
ELECTRICITY
PHYSICS
TRANSMISSION
Title Federated learning for client-specific neural network parameter generation for wireless communication
URI https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20240220&DB=EPODOC&locale=&CC=US&NR=11909482B2
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LS8NAEB5Kfd40KlofrCC5Bdu8cwhC86AIfWAb6a1sNmlRYlpsxL_vzJLaXvS0sMsu2YFvZjY737cAD8KxPExb55rtOp5m6npHc1Mn1_TU8vJOxi3DJqJwf2D3EvN5ak0b8L7hwkid0G8pjoiIEoj3Svrr1fYnVihrK9eP6Rt2LZ_iiR-q9emYrgr0thp2_Wg0DIeBGgR-MlYHL34HA59nunoX3fUeptEOoSF67RIrZbUbUuIT2B_hamV1Co28VOAo2Ly8psBhv77wVuBAVmiKNXbWKFyfQR6TAgTOzlj96MOCYe7JREHkRo3Ik1QAxEirkhfYyEpvRirfH1T9whZSa5p2KeeRXHGBHo-JXbbIOdzH0SToafjls18zzZLxdpPGBTTLZZlfAnMdBC3HUx4pwwkn9TJucp61TYML10qzK2j9vU7rv8FrOCaTS4J3-waa1edXfoshukrvpG1_AKvkl9Y
link.rule.ids 230,309,783,888,25576,76876
linkProvider European Patent Office
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LS8NAEB5KfdSbVqXW1wqSW7DNo0kOQUjSELUvbCu9lc0mFqWmxUb8-84sqe1FTwu77JId-GZms_N9C3ArLNPBtPVVbdmWoxqa1lTt2EpVLTadtJlwU28RUbjba0Vj43FiTkrwvubCSJ3QbymOiIgSiPdc-uvl5idWIGsrV3fxG3Yt7sORGyjF6ZiuCrSGEnhue9AP-r7i--54qPSe3SYGPsewNQ_d9Q6m2Bahof3iEStluR1SwkPYHeBqWX4EpTSrQsVfv7xWhf1uceFdhT1ZoSlW2FmgcHUMaUgKEDg7YcWjDzOGuScTcyI3qkSepAIgRlqVfI6NrPRmpPL9QdUvbCa1pmmXch7JFc_R4zGxzRY5gZuwPfIjFb98-mum6Xi42aR-CuVskaU1YLaFoOV4yiNlOGHFTsINzpOGoXNhm3FyBvW_16n_N3gNlWjU7Uw7D72nczgg80uyd-MCyvnnV3qJ4TqPr6SdfwD4T5rJ
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=Federated+learning+for+client-specific+neural+network+parameter+generation+for+wireless+communication&rft.inventor=Bhushan%2C+Naga&rft.inventor=Yoo%2C+Taesang&rft.inventor=Sundararajan%2C+Jay+Kumar&rft.inventor=Mukkavilli%2C+Krishna+Kiran&rft.inventor=Kwon%2C+Hwan+Joon&rft.inventor=Namgoong%2C+June&rft.inventor=Ji%2C+Tingfang&rft.inventor=Vitthaladevuni%2C+Pavan+Kumar&rft.date=2024-02-20&rft.externalDBID=B2&rft.externalDocID=US11909482B2