Federated Learning Over Wireless Device-to-Device Networks: Algorithms and Convergence Analysis

The proliferation of Internet-of-Things (IoT) devices and cloud-computing applications over siloed data centers is motivating renewed interest in the collaborative training of a shared model by multiple individual clients via federated learning (FL). To improve the communication efficiency of FL imp...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE journal on selected areas in communications Ročník 39; číslo 12; s. 3723 - 3741
Hlavní autoři:	Xing, Hong, Simeone, Osvaldo, Bi, Suzhi
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.12.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Algorithms Channel noise Clients Cloud computing Collaborative work Convergence Convexity D2D networks Data centers Data models decentralized stochastic gradient descent Device-to-device communication distributed learning Federated learning Image classification Internet of Things Machine learning over-the-air computation random linear coding Signal to noise ratio Stochastic processes Topology Wireless communications Wireless networks
ISSN:	0733-8716, 1558-0008
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	The proliferation of Internet-of-Things (IoT) devices and cloud-computing applications over siloed data centers is motivating renewed interest in the collaborative training of a shared model by multiple individual clients via federated learning (FL). To improve the communication efficiency of FL implementations in wireless systems, recent works have proposed compression and dimension reduction mechanisms, along with digital and analog transmission schemes that account for channel noise, fading, and interference. The prior art has mainly focused on star topologies consisting of distributed clients and a central server. In contrast, this paper studies FL over wireless device-to-device (D2D) networks by providing theoretical insights into the performance of digital and analog implementations of decentralized stochastic gradient descent (DSGD). First, we introduce generic digital and analog wireless implementations of communication-efficient DSGD algorithms, leveraging random linear coding (RLC) for compression and over-the-air computation (AirComp) for simultaneous analog transmissions. Next, under the assumptions of convexity and connectivity, we provide convergence bounds for both implementations. The results demonstrate the dependence of the optimality gap on the connectivity and on the signal-to-noise ratio (SNR) levels in the network. The analysis is corroborated by experiments on an image-classification task.
AbstractList	The proliferation of Internet-of-Things (IoT) devices and cloud-computing applications over siloed data centers is motivating renewed interest in the collaborative training of a shared model by multiple individual clients via federated learning (FL). To improve the communication efficiency of FL implementations in wireless systems, recent works have proposed compression and dimension reduction mechanisms, along with digital and analog transmission schemes that account for channel noise, fading, and interference. The prior art has mainly focused on star topologies consisting of distributed clients and a central server. In contrast, this paper studies FL over wireless device-to-device (D2D) networks by providing theoretical insights into the performance of digital and analog implementations of decentralized stochastic gradient descent (DSGD). First, we introduce generic digital and analog wireless implementations of communication-efficient DSGD algorithms, leveraging random linear coding (RLC) for compression and over-the-air computation (AirComp) for simultaneous analog transmissions. Next, under the assumptions of convexity and connectivity, we provide convergence bounds for both implementations. The results demonstrate the dependence of the optimality gap on the connectivity and on the signal-to-noise ratio (SNR) levels in the network. The analysis is corroborated by experiments on an image-classification task.
Author	Xing, Hong Simeone, Osvaldo Bi, Suzhi
Author_xml	– sequence: 1 givenname: Hong orcidid: 0000-0001-5206-1225 surname: Xing fullname: Xing, Hong email: hong.xing@szu.edu.cn organization: College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China – sequence: 2 givenname: Osvaldo orcidid: 0000-0001-9898-3209 surname: Simeone fullname: Simeone, Osvaldo email: osvaldo.simeone@kcl.ac.uk organization: Department of Engineering, King’s Communications, Learning & Information Processing (KCLIP) Lab, King's College London, London, U.K – sequence: 3 givenname: Suzhi orcidid: 0000-0001-6212-690X surname: Bi fullname: Bi, Suzhi email: bsz@szu.edu.cn organization: College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China
BookMark	eNp9kE1PwzAMhiM0JDbgByAulTh32G36xW0ajA9NcADEMcoadwS6ZCQZaP-eTkUcOCAf7MP72NYzYgNjDTF2gjBGhOr87nEyHSeQ4DhFLDnAHhtilpUxAJQDNoQiTeOywPyAjbx_A0DOy2TIxIwUORlIRXOSzmizjB4-yUUv2lFL3keX9KlrioON-ym6p_Bl3bu_iCbt0jodXlc-kkZFU2s6ckmmC02MbLde-yO238jW0_FPP2TPs6un6U08f7i-nU7mcZ2meYgbSOpcEfEmqxdccpBZJlEVC2gQOEeQdYmKsK4WOSQl5YqngGWhpKwUpyY9ZGf93rWzHxvyQbzZjeue8CLJqiqBKs-hS2Gfqp313lEj1k6vpNsKBLHzKHYexc6j-PHYMcUfptZBBm1NcFK3_5KnPamJ6PdSleVp0tU3EziChQ
CODEN	ISACEM
CitedBy_id	crossref_primary_10_1016_j_comcom_2024_06_001 crossref_primary_10_1109_TCOMM_2024_3435072 crossref_primary_10_1002_spe_3399 crossref_primary_10_1109_TSP_2024_3358615 crossref_primary_10_1109_TGCN_2022_3186439 crossref_primary_10_1109_TMC_2024_3507381 crossref_primary_10_1109_TMC_2024_3364673 crossref_primary_10_1109_JSAC_2021_3118346 crossref_primary_10_1109_JSTSP_2022_3223498 crossref_primary_10_1109_TWC_2022_3185074 crossref_primary_10_1109_TVT_2023_3234550 crossref_primary_10_1109_TSP_2024_3368751 crossref_primary_10_1109_TWC_2024_3425732 crossref_primary_10_1109_JSAC_2022_3223408 crossref_primary_10_1109_TC_2023_3239542 crossref_primary_10_1109_TMC_2024_3509852 crossref_primary_10_1109_TSIPN_2024_3423668 crossref_primary_10_1109_ACCESS_2024_3418900 crossref_primary_10_1109_JIOT_2024_3352280 crossref_primary_10_3390_app14124989 crossref_primary_10_1109_TVT_2023_3322461 crossref_primary_10_1109_TVT_2024_3506950 crossref_primary_10_1109_TSP_2023_3284381 crossref_primary_10_1109_OJSP_2025_3557332 crossref_primary_10_1109_TWC_2022_3172147 crossref_primary_10_1109_TWC_2023_3327610 crossref_primary_10_1109_TCOMM_2024_3362143 crossref_primary_10_1109_TSP_2025_3546328 crossref_primary_10_1109_TNSM_2022_3232381 crossref_primary_10_1109_TNNLS_2025_3552406 crossref_primary_10_1109_JSEN_2025_3536518 crossref_primary_10_1109_JIOT_2025_3530265 crossref_primary_10_1016_j_compbiomed_2023_107861 crossref_primary_10_1109_JSAC_2021_3118406 crossref_primary_10_1109_JSAC_2021_3118400 crossref_primary_10_1109_TWC_2024_3479769 crossref_primary_10_1109_JSAC_2022_3223661 crossref_primary_10_1109_JIOT_2024_3407584 crossref_primary_10_1109_MNET_011_2300046 crossref_primary_10_1109_JIOT_2023_3329128 crossref_primary_10_1109_JIOT_2024_3481257 crossref_primary_10_1109_TCC_2023_3285534 crossref_primary_10_1109_TITS_2024_3361666 crossref_primary_10_1109_TWC_2024_3407822 crossref_primary_10_1109_JSTSP_2024_3374591 crossref_primary_10_1109_TWC_2023_3271854 crossref_primary_10_1109_TSP_2024_3460690 crossref_primary_10_1109_TCOMM_2024_3407208 crossref_primary_10_1109_JIOT_2024_3400512 crossref_primary_10_1109_JIOT_2025_3534898 crossref_primary_10_1109_LSP_2023_3347151 crossref_primary_10_1016_j_comcom_2024_107964 crossref_primary_10_1109_OJCOMS_2025_3574098 crossref_primary_10_1109_MWC_005_2300016
Cites_doi	10.1109/TWC.2019.2946245 10.1109/JPROC.2019.2918951 10.1109/JPROC.2018.2817461 10.1109/ISIT45174.2021.9517780 10.1109/JSAC.2021.3126060 10.1109/MSP.2020.2970170 10.1109/CDC42340.2020.9303828 10.1109/TCOMM.2021.3078783 10.1109/TWC.2020.3024629 10.1017/CBO9781139519793.016 10.1109/SPAWC48557.2020.9154309 10.1109/JSAC.2021.3118400 10.1109/TWC.2020.2974748 10.1561/9781680837896 10.1109/SPAWC48557.2020.9154332 10.1017/CBO9781139042918 10.1109/MSP.2020.2975749 10.1109/MCOM.001.1900103 10.1109/CAMAD50429.2020.9209305 10.1109/GLOBECOM42002.2020.9322286 10.1109/ICC47138.2019.9123209 10.1137/1.9781611976014.13 10.1109/PIMRC.2019.8904164 10.1109/JIOT.2020.3002925 10.1016/j.sysconle.2004.02.022
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID	97E RIA RIE AAYXX CITATION 7SP 8FD L7M
DOI	10.1109/JSAC.2021.3118400
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore CrossRef Electronics & Communications Abstracts Technology Research Database Advanced Technologies Database with Aerospace
DatabaseTitle	CrossRef Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts
DatabaseTitleList	Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1558-0008
EndPage	3741
ExternalDocumentID	10_1109_JSAC_2021_3118400 9563232
Genre	orig-research
GrantInformation_xml	– fundername: Key Project of Department of Education of Guangdong Province grantid: 2020ZDZX3050 funderid: 10.13039/501100010226 – fundername: National Natural Science Foundation of China grantid: 61901279; 61871271 funderid: 10.13039/501100001809 – fundername: Natural Science Foundation of Guangdong Province grantid: 2020A1515011484 funderid: 10.13039/501100003453 – fundername: European Research Council (ERC) through the European Union’s Horizon 2020 Research and Innovation Programme grantid: 725731 funderid: 10.13039/501100000781 – fundername: National Key Research and Development Program of China grantid: 2019YFB1803305 funderid: 10.13039/501100012166 – fundername: Guangdong Province Pearl River Scholar Funding Scheme 2018
GroupedDBID	-~X .DC 0R~ 29I 3EH 4.4 41~ 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT ADRHT AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 IBMZZ ICLAB IES IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS TN5 VH1 AAYXX CITATION 7SP 8FD L7M
ID	FETCH-LOGICAL-c336t-f02c6dee4f5cb4a40a55a1d7b0f104410ac81de1c9b6028e6d430187daa9d4ef3
IEDL.DBID	RIE
ISICitedReferencesCount	77
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000720517900013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0733-8716
IngestDate	Mon Jun 30 10:13:50 EDT 2025 Tue Nov 18 21:38:55 EST 2025 Sat Nov 29 03:23:04 EST 2025 Wed Aug 27 02:26:04 EDT 2025
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	12
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c336t-f02c6dee4f5cb4a40a55a1d7b0f104410ac81de1c9b6028e6d430187daa9d4ef3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0001-9898-3209 0000-0001-6212-690X 0000-0001-5206-1225
OpenAccessLink	http://www.scopus.com/inward/record.url?scp=85117114243&partnerID=8YFLogxK
PQID	2599209660
PQPubID	85481
PageCount	19
ParticipantIDs	ieee_primary_9563232 proquest_journals_2599209660 crossref_primary_10_1109_JSAC_2021_3118400 crossref_citationtrail_10_1109_JSAC_2021_3118400
PublicationCentury	2000
PublicationDate	2021-12-01
PublicationDateYYYYMMDD	2021-12-01
PublicationDate_xml	– month: 12 year: 2021 text: 2021-12-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE journal on selected areas in communications
PublicationTitleAbbrev	J-SAC
PublicationYear	2021
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref35 ref15 vogels (ref23) 2020 ref36 ref31 nedi? (ref16) 2018; 106 ref30 ref33 wu (ref11) 2018 ref32 ref10 ref2 ref1 ref39 ref38 guha roy (ref13) 2019 research (ref14) 2017 bernstein (ref9) 2018 alistarh (ref8) 2017 xiao (ref41) 2017 sun (ref18) 2021 ref24 ref26 ref25 koloskova (ref21) 2020 ref22 abari (ref37) 2016 koloskova (ref20) 2019 stich (ref40) 2018 ref28 ref27 tang (ref19) 2018 ref29 saha (ref34) 2020 ref7 ref4 xin (ref17) 2019 ref3 ref6 ref5 basu (ref12) 2019
References_xml	– year: 2017 ident: ref8 article-title: QSGD: Communication-efficient SGD via gradient quantization and encoding publication-title: Proc Adv Neural Inf Process Syst (NeurIPS) – ident: ref24 doi: 10.1109/TWC.2019.2946245 – year: 2020 ident: ref23 article-title: Practical low-rank communication compression in decentralized deep learning publication-title: Proc Adv Neural Inf Process Syst (NeurIPS) – year: 2019 ident: ref20 article-title: Decentralized stochastic optimization and gossip algorithms with compressed communication publication-title: Proc Int Conf Mach Learn (ICML) – year: 2016 ident: ref37 article-title: Over-the-air function computation in sensor networks publication-title: arXiv 1612 02307 – ident: ref6 doi: 10.1109/JPROC.2019.2918951 – year: 2017 ident: ref41 article-title: Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms publication-title: ArXiv 1708 07747 – volume: 106 start-page: 953 year: 2018 ident: ref16 article-title: Network topology and communication-computation tradeoffs in decentralized optimization publication-title: Proc IEEE doi: 10.1109/JPROC.2018.2817461 – year: 2017 ident: ref14 publication-title: Bringing HPC Techniques to Deep Learning – year: 2018 ident: ref19 article-title: $D^{2}$ : Decentralized training over decentralized data publication-title: Proc Int Conf Mach Learn (ICML) – ident: ref33 doi: 10.1109/ISIT45174.2021.9517780 – ident: ref25 doi: 10.1109/JSAC.2021.3126060 – ident: ref3 doi: 10.1109/MSP.2020.2970170 – ident: ref22 doi: 10.1109/CDC42340.2020.9303828 – ident: ref27 doi: 10.1109/TCOMM.2021.3078783 – year: 2019 ident: ref13 article-title: BrainTorrent: A peer-to-peer environment for decentralized federated learning publication-title: arXiv 1905 06731 – ident: ref26 doi: 10.1109/TWC.2020.3024629 – year: 2020 ident: ref21 article-title: Decentralized deep learning with arbitrary communication compression publication-title: Proc Int Conf Learn Represent (ICLR) – year: 2019 ident: ref17 article-title: An introduction to decentralized stochastic optimization with gradient tracking publication-title: arXiv 1907 09648 – ident: ref35 doi: 10.1017/CBO9781139519793.016 – ident: ref10 doi: 10.1109/SPAWC48557.2020.9154309 – ident: ref38 doi: 10.1109/JSAC.2021.3118400 – ident: ref15 doi: 10.1109/TWC.2020.2974748 – ident: ref4 doi: 10.1561/9781680837896 – year: 2020 ident: ref34 article-title: Decentralized optimization over noisy, rate-constrained networks: Achieving consensus by communicating differences publication-title: arXiv 2010 11292 – year: 2019 ident: ref12 article-title: Qsparse-local-SGD: Distributed SGD with quantization, sparsification and local computations publication-title: Proc Adv Neural Inf Process Syst (NeurIPS) – ident: ref1 doi: 10.1109/SPAWC48557.2020.9154332 – ident: ref2 doi: 10.1017/CBO9781139042918 – ident: ref5 doi: 10.1109/MSP.2020.2975749 – year: 2021 ident: ref18 article-title: Decentralized federated averaging publication-title: arXiv 2104 11375 – ident: ref7 doi: 10.1109/MCOM.001.1900103 – ident: ref31 doi: 10.1109/CAMAD50429.2020.9209305 – year: 2018 ident: ref40 article-title: Sparsified SGD with memory publication-title: Proc Adv Neural Inf Process Syst (NeurIPS) – ident: ref32 doi: 10.1109/GLOBECOM42002.2020.9322286 – ident: ref30 doi: 10.1109/ICC47138.2019.9123209 – ident: ref36 doi: 10.1137/1.9781611976014.13 – ident: ref28 doi: 10.1109/PIMRC.2019.8904164 – ident: ref29 doi: 10.1109/JIOT.2020.3002925 – year: 2018 ident: ref9 article-title: signSGD: Compressed optimisation for non-convex problems publication-title: Proc Int Conf Mach Learn (ICML) – year: 2018 ident: ref11 article-title: Error compensated quantized SGD and its applications to large-scale distributed optimization publication-title: Proc Int Conf Mach Learn (ICML) – ident: ref39 doi: 10.1016/j.sysconle.2004.02.022
SSID	ssj0014482
Score	2.657895
Snippet	The proliferation of Internet-of-Things (IoT) devices and cloud-computing applications over siloed data centers is motivating renewed interest in the...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	3723
SubjectTerms	Algorithms Channel noise Clients Cloud computing Collaborative work Convergence Convexity D2D networks Data centers Data models decentralized stochastic gradient descent Device-to-device communication distributed learning Federated learning Image classification Internet of Things Machine learning over-the-air computation random linear coding Signal to noise ratio Stochastic processes Topology Wireless communications Wireless networks
Title	Federated Learning Over Wireless Device-to-Device Networks: Algorithms and Convergence Analysis
URI	https://ieeexplore.ieee.org/document/9563232 https://www.proquest.com/docview/2599209660
Volume	39
WOSCitedRecordID	wos000720517900013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-0008 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014482 issn: 0733-8716 databaseCode: RIE dateStart: 19830101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB5UPOjBt1hf5OBJjCab3cR4K9UiHqqggrclm2S1UFtpV3-_mey2KIrgLYdkWTLJzHyZmW8AjoJJd0mRFZQn3NLUWUUNywyVMjNo0EShythsQvV6509P-m4OTma1MN77mHzmT3EYY_luZN_xqews-PIieADzMK-UrGu1ZhGDADNixEAJQREENBFMzvTZzX27E5BgwgNARUDDvtmg2FTlhyaO5qW7-r8fW4OVxo0k7Vru6zDnhxuw_IVccBPyLvJEBFfSkYZE9ZnchoNLMOF1EBQcufSoJmg1ovWI9Oqc8MkFaQ-eR-N-9fI6IWboSAdz02OZpidTGpMteOxePXSuadNOgVohZEVLlljpvE_LzBapSZnJMsOdKlgZMFnKmbHBefXc6kIGr8NLlwps2eeM0S71pdiGheFo6HeAZNpq7rQq8SlSJPq8MFIWygjteCkcawGbbnBuG65xbHkxyCPmYDpHmeQok7yRSQuOZ0veaqKNvyZvohBmE5v9b8H-VIp5cxUnecB3OmFIQrr7-6o9WMJv1zkq-7BQjd_9ASzaj6o_GR_GU_YJDq3Oug
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Nb9QwEB0tLRL0QAvbii398IETwtSOnaTmttp2VaAEJIrUm-XYTltp2aDdtL-_HicbUYGQevPBViKPPTPPM_MG4G0w6S4p05LyhFsqnc2pYamhWZYaNGiizKvYbCIviuPLS_V9AO_7WhjvfUw-8x9wGGP5rra3-FR2FHx5ETyAJ7CeSpmwtlqrjxkEoBFjBrkQFGFAF8PkTB19_jGeBCyY8ABREdKwB1YotlX5SxdHAzPdfNyvbcGLzpEk41byL2Hg569g4w96wSHoKTJFBGfSkY5G9Yp8C0eXYMrrLKg4cuJRUdCmpu2IFG1W-PIjGc-u6sVNc_1rSczckQlmp8dCTU9WRCbb8HN6ejE5o11DBWqFyBpascRmzntZpbaURjKTpoa7vGRVQGWSM2OD--q5VWUW_A6fOSmwaZ8zRjnpK7EDa_N67l8DSZVV3Km8wsdIkajj0mRZmRuhHK-EYyNgqw3WtmMbx6YXMx1RB1MaZaJRJrqTyQje9Ut-t1Qb_5s8RCH0E7v9H8HeSoq6u4xLHRCeShjSkO7-e9UhPDu7-Hquzz8VX97Ac_xOm7GyB2vN4tbvw1N719wsFwfxxN0D-N_SAQ
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%3Ajournal&rft.genre=article&rft.atitle=Federated+Learning+Over+Wireless+Device-to-Device+Networks%3A+Algorithms+and+Convergence+Analysis&rft.jtitle=IEEE+journal+on+selected+areas+in+communications&rft.au=Xing%2C+Hong&rft.au=Simeone%2C+Osvaldo&rft.au=Bi%2C+Suzhi&rft.date=2021-12-01&rft.issn=0733-8716&rft.eissn=1558-0008&rft.volume=39&rft.issue=12&rft.spage=3723&rft.epage=3741&rft_id=info:doi/10.1109%2FJSAC.2021.3118400&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_JSAC_2021_3118400
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0733-8716&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0733-8716&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0733-8716&client=summon