Deep Learning for Distributed Channel Feedback and Multiuser Precoding in FDD Massive MIMO

This paper shows that deep neural network (DNN) can be used for efficient and distributed channel estimation, quantization, feedback, and downlink multiuser precoding for a frequency-division duplex massive multiple-input multiple-output system in which a base station (BS) serves multiple mobile use...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on wireless communications Vol. 20; no. 7; pp. 4044 - 4057
Main Authors:	Sohrabi, Foad, Attiah, Kareem M., Yu, Wei
Format:	Journal Article
Language:	English
Published:	New York IEEE 01.07.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Artificial neural networks Channel estimation Deep learning deep neural network (DNN) distributed source coding (DSC) Downlink downlink precoding Estimation Feedback feedback frequency-division duplex (FDD) Frequency division duplexing Machine learning massive multiple-input multiple-output (MIMO) Precoding quantization Quantization (signal) Radio equipment Robust design Training
ISSN:	1536-1276, 1558-2248
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	This paper shows that deep neural network (DNN) can be used for efficient and distributed channel estimation, quantization, feedback, and downlink multiuser precoding for a frequency-division duplex massive multiple-input multiple-output system in which a base station (BS) serves multiple mobile users, but with rate-limited feedback from the users to the BS. A key observation is that the multiuser channel estimation and feedback problem can be thought of as a distributed source coding problem. In contrast to the traditional approach where the channel state information (CSI) is estimated and quantized at each user independently, this paper shows that a joint design of pilots and a new DNN architecture, which maps the received pilots directly into feedback bits at the user side then maps the feedback bits from all the users directly into the precoding matrix at the BS, can significantly improve the overall performance. This paper further proposes robust design strategies with respect to channel parameters and also a generalizable DNN architecture for varying number of users and number of feedback bits. Numerical results show that the DNN-based approach with short pilot sequences and very limited feedback overhead can already approach the performance of conventional linear precoding schemes with full CSI.
AbstractList	This paper shows that deep neural network (DNN) can be used for efficient and distributed channel estimation, quantization, feedback, and downlink multiuser precoding for a frequency-division duplex massive multiple-input multiple-output system in which a base station (BS) serves multiple mobile users, but with rate-limited feedback from the users to the BS. A key observation is that the multiuser channel estimation and feedback problem can be thought of as a distributed source coding problem. In contrast to the traditional approach where the channel state information (CSI) is estimated and quantized at each user independently, this paper shows that a joint design of pilots and a new DNN architecture, which maps the received pilots directly into feedback bits at the user side then maps the feedback bits from all the users directly into the precoding matrix at the BS, can significantly improve the overall performance. This paper further proposes robust design strategies with respect to channel parameters and also a generalizable DNN architecture for varying number of users and number of feedback bits. Numerical results show that the DNN-based approach with short pilot sequences and very limited feedback overhead can already approach the performance of conventional linear precoding schemes with full CSI.
Author	Yu, Wei Sohrabi, Foad Attiah, Kareem M.
Author_xml	– sequence: 1 givenname: Foad orcidid: 0000-0002-7514-2578 surname: Sohrabi fullname: Sohrabi, Foad email: fsohrabi@ece.utoronto.ca organization: The Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada – sequence: 2 givenname: Kareem M. orcidid: 0000-0001-8838-9687 surname: Attiah fullname: Attiah, Kareem M. email: kattiah@ece.utoronto.ca organization: The Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada – sequence: 3 givenname: Wei orcidid: 0000-0002-7453-422X surname: Yu fullname: Yu, Wei email: weiyu@ece.utoronto.ca organization: The Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, Toronto, Canada
BookMark	eNp9kMFLwzAUh4NMcJveBS8Bz51p0jTtUVqng5V5mAheSpq-amZNZ5IK_ve2bHjw4On9Dr_vPd43QxPTGUDoMiSLMCTpzfY5W1BCwwUjnA_hBE1DzpOA0iiZjJnFQUhFfIZmzu0ICUXM-RS95AB7vAZpjTavuOkszrXzVle9hxpnb9IYaPESoK6kesfS1LjoW697BxY_WlBdPYLa4GWe40I6p78AF6tic45OG9k6uDjOOXpa3m2zh2C9uV9lt-tAMS58AClLlRSgKMQq5ioBFqU1ow2TdVWp4bmGsghILKtICM4FF2nMVBJBJCCRFZuj68Peve0-e3C-3HW9NcPJkvIoHRAu2NCKDy1lO-csNKXSXnrdGW-lbsuQlKPHcvBYjh7Lo8cBJH_AvdUf0n7_h1wdEA0Av_WURSKhhP0AJSR-ZA
CODEN	ITWCAX
CitedBy_id	crossref_primary_10_1109_TCOMM_2022_3209887 crossref_primary_10_1007_s42835_021_00778_6 crossref_primary_10_1109_TCOMM_2023_3282227 crossref_primary_10_1109_TWC_2022_3149946 crossref_primary_10_1109_JSEN_2025_3526977 crossref_primary_10_1109_TCOMM_2021_3120294 crossref_primary_10_1109_TWC_2022_3170104 crossref_primary_10_1109_TWC_2024_3381211 crossref_primary_10_3390_e24040441 crossref_primary_10_1109_TWC_2022_3215104 crossref_primary_10_1109_TWC_2022_3218579 crossref_primary_10_1109_JSAC_2022_3196064 crossref_primary_10_1016_j_phycom_2024_102516 crossref_primary_10_1109_JSAC_2025_3559124 crossref_primary_10_3390_telecom5010011 crossref_primary_10_1109_JSAC_2025_3559165 crossref_primary_10_1109_TCOMM_2022_3180388 crossref_primary_10_1109_TVT_2024_3422663 crossref_primary_10_1109_TCOMM_2022_3199489 crossref_primary_10_1109_TWC_2023_3336911 crossref_primary_10_1016_j_phycom_2023_102193 crossref_primary_10_1109_TWC_2022_3141653 crossref_primary_10_1109_JSYST_2024_3357712 crossref_primary_10_1109_ACCESS_2022_3232855 crossref_primary_10_1109_TWC_2023_3275990 crossref_primary_10_1109_MBITS_2024_3504521 crossref_primary_10_1109_LCOMM_2022_3156946 crossref_primary_10_1109_JSAC_2023_3240781 crossref_primary_10_1109_TWC_2024_3422399 crossref_primary_10_1109_JSAC_2021_3126050 crossref_primary_10_1109_TWC_2021_3111843 crossref_primary_10_1109_LCOMM_2023_3342166 crossref_primary_10_1109_MBITS_2022_3212978 crossref_primary_10_1007_s40031_024_01131_x crossref_primary_10_3389_fncom_2024_1345644 crossref_primary_10_3390_s22010309 crossref_primary_10_1109_ACCESS_2022_3208284 crossref_primary_10_1109_LWC_2022_3193093 crossref_primary_10_1109_TCOMM_2022_3143122 crossref_primary_10_1109_TVT_2023_3327276 crossref_primary_10_1016_j_dsp_2025_105515 crossref_primary_10_1109_TWC_2023_3299338 crossref_primary_10_1109_JSAC_2021_3087269 crossref_primary_10_1109_TWC_2023_3250227 crossref_primary_10_1109_TVT_2024_3452409 crossref_primary_10_1109_TWC_2024_3516633 crossref_primary_10_1109_TVT_2021_3110608 crossref_primary_10_1109_TWC_2022_3219840 crossref_primary_10_1007_s11432_023_3838_4 crossref_primary_10_1007_s11277_023_10748_y crossref_primary_10_1109_JSAC_2022_3221976 crossref_primary_10_1109_TSP_2022_3213488 crossref_primary_10_1109_JSAC_2021_3126076 crossref_primary_10_1109_TWC_2022_3181219 crossref_primary_10_3390_electronics11193023 crossref_primary_10_1109_TWC_2021_3120926 crossref_primary_10_1109_TWC_2023_3330902 crossref_primary_10_1109_TCOMM_2024_3403498 crossref_primary_10_1109_TWC_2023_3324621 crossref_primary_10_1016_j_iot_2024_101406 crossref_primary_10_1109_TCOMM_2022_3141399 crossref_primary_10_1109_JSTSP_2022_3160268 crossref_primary_10_1002_ett_4797 crossref_primary_10_1109_TWC_2025_3543392 crossref_primary_10_1109_LWC_2024_3509612 crossref_primary_10_1109_LWC_2024_3452486 crossref_primary_10_1109_TCOMM_2023_3317924 crossref_primary_10_1109_TWC_2022_3187790 crossref_primary_10_1109_TWC_2025_3542798 crossref_primary_10_1109_TWC_2023_3327984 crossref_primary_10_1109_JSAC_2021_3087234 crossref_primary_10_1109_TCOMM_2021_3133939 crossref_primary_10_1109_TWC_2022_3170576 crossref_primary_10_1080_00207217_2024_2302341 crossref_primary_10_1109_JSAC_2024_3460084 crossref_primary_10_1109_TWC_2022_3163249 crossref_primary_10_1109_TCOMM_2024_3511954 crossref_primary_10_1109_ACCESS_2022_3174095 crossref_primary_10_1109_MCOM_001_2400285 crossref_primary_10_1109_TWC_2025_3562818 crossref_primary_10_1109_LCOMM_2022_3179236 crossref_primary_10_3390_s21165298 crossref_primary_10_1109_TCOMM_2021_3086525 crossref_primary_10_1109_TCOMM_2022_3217777 crossref_primary_10_1109_TWC_2022_3191605 crossref_primary_10_3390_s23094359 crossref_primary_10_1109_ACCESS_2022_3202640 crossref_primary_10_1109_TWC_2024_3496933
Cites_doi	10.1109/TIT.2011.2158882 10.1109/JSAC.2019.2904352 10.1109/JSTSP.2018.2819135 10.1109/TIT.1973.1055037 10.1109/JSAC.2014.2328098 10.1109/IEEECONF44664.2019.9048810 10.1109/TSP.2019.2899805 10.1109/TIT.1979.1056022 10.1109/TIT.2007.904785 10.1109/TIT.1976.1055508 10.1109/TIT.2007.909108 10.1073/pnas.0909892106 10.1109/TSP.2014.2324991 10.1109/PIMRC.2019.8904332 10.1109/TVT.2019.2893928 10.1109/TSP.2015.2463260 10.1109/MSP.2004.1328091 10.1017/CBO9781139030687 10.1109/TWC.2010.092810.091092 10.1109/TIT.2007.892784 10.1109/GLOCOM.2007.829 10.1109/LWC.2020.3019321 10.1109/LWC.2019.2962114 10.1109/JSAC.2008.081002 10.1109/TWC.2015.2455980 10.1109/LCOMM.2020.2983018 10.1109/LCOMM.2018.2882829 10.1109/MCOM.2016.7402270 10.1109/JSTSP.2016.2520912 10.1109/ICASSP40776.2020.9054488 10.1109/TIT.2010.2046225 10.1109/WCNC.2012.6214417 10.1109/LWC.2018.2818160 10.1109/JSAIT.2020.2986467 10.1109/MCOM.2011.5783993
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 7SC 7SP 8FD JQ2 L7M L~C L~D
DOI	10.1109/TWC.2021.3055202
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
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	1558-2248
EndPage	4057
ExternalDocumentID	10_1109_TWC_2021_3055202 9347820
Genre	orig-research
GrantInformation_xml	– fundername: Huawei Technologies Canada funderid: 10.13039/501100003816
GroupedDBID	-~X 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AIBXA AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 IES IFIPE IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c357t-e939ca7ec2e6c65c8e349d32f3adbbc110f234e06ab47755757963c84e47e8ab3
IEDL.DBID	RIE
ISICitedReferencesCount	111
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000671527500002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1536-1276
IngestDate	Fri Jul 25 09:23:55 EDT 2025 Sat Nov 29 06:23:51 EST 2025 Tue Nov 18 22:22:55 EST 2025 Wed Aug 27 02:26:38 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	7
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c357t-e939ca7ec2e6c65c8e349d32f3adbbc110f234e06ab47755757963c84e47e8ab3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-7514-2578 0000-0002-7453-422X 0000-0001-8838-9687
PQID	2549755573
PQPubID	105736
PageCount	14
ParticipantIDs	proquest_journals_2549755573 crossref_citationtrail_10_1109_TWC_2021_3055202 crossref_primary_10_1109_TWC_2021_3055202 ieee_primary_9347820
PublicationCentury	2000
PublicationDate	2021-July 2021-7-00 20210701
PublicationDateYYYYMMDD	2021-07-01
PublicationDate_xml	– month: 07 year: 2021 text: 2021-July
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on wireless communications
PublicationTitleAbbrev	TWC
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	ref13 ref34 ref12 ref37 ref15 ref36 ref14 ref31 ref30 guo (ref38) 2020 ref33 ref11 ref32 ref10 hinton (ref42) 2012 ref2 ref1 chung (ref21) 2016 ref17 ref16 ref18 bengio (ref20) 2013 chollet (ref44) 2015 kingma (ref45) 2014 abadi (ref43) 2016 mashhadi (ref39) 2020 ref23 donoho (ref27) 2009; 106 ref26 rao (ref24) 2014; 62 ref25 ref41 ref22 ref28 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ioffe (ref46) 2015 ref40 hinton (ref19) 2012 mashhadi (ref35) 2020
References_xml	– ident: ref17 doi: 10.1109/TIT.2011.2158882 – ident: ref5 doi: 10.1109/JSAC.2019.2904352 – ident: ref31 doi: 10.1109/JSTSP.2018.2819135 – ident: ref10 doi: 10.1109/TIT.1973.1055037 – ident: ref6 doi: 10.1109/JSAC.2014.2328098 – year: 2012 ident: ref42 article-title: Improving neural networks by preventing co-adaptation of feature detectors publication-title: arXiv 1207 0580 – ident: ref3 doi: 10.1109/IEEECONF44664.2019.9048810 – ident: ref1 doi: 10.1109/TSP.2019.2899805 – ident: ref14 doi: 10.1109/TIT.1979.1056022 – ident: ref16 doi: 10.1109/TIT.2007.904785 – ident: ref11 doi: 10.1109/TIT.1976.1055508 – year: 2012 ident: ref19 article-title: Neural networks for machine learning publication-title: The course of lectures – ident: ref28 doi: 10.1109/TIT.2007.909108 – year: 2020 ident: ref39 article-title: Distributed deep convolutional compression for massive MIMO CSI feedback publication-title: IEEE Trans Wireless Commun – volume: 106 start-page: 18914 year: 2009 ident: ref27 article-title: Message-passing algorithms for compressed sensing publication-title: Proc Nat Acad Sci USA doi: 10.1073/pnas.0909892106 – volume: 62 start-page: 3261 year: 2014 ident: ref24 article-title: Distributed compressive CSIT estimation and feedback for FDD multi-user massive MIMO systems publication-title: IEEE Trans Signal Process doi: 10.1109/TSP.2014.2324991 – ident: ref29 doi: 10.1109/PIMRC.2019.8904332 – year: 2016 ident: ref21 article-title: Hierarchical multiscale recurrent neural networks publication-title: arXiv 1609 01704 – year: 2015 ident: ref44 publication-title: Keras – ident: ref2 doi: 10.1109/TVT.2019.2893928 – ident: ref23 doi: 10.1109/TSP.2015.2463260 – ident: ref12 doi: 10.1109/MSP.2004.1328091 – year: 2020 ident: ref38 article-title: DL-based CSI feedback and cooperative recovery in massive MIMO publication-title: arXiv 2003 03303 – ident: ref13 doi: 10.1017/CBO9781139030687 – ident: ref7 doi: 10.1109/TWC.2010.092810.091092 – year: 2014 ident: ref45 article-title: Adam: A method for stochastic optimization publication-title: arXiv 1412 6980 – year: 2020 ident: ref35 article-title: Pruning the pilots: Deep learning-based pilot design and channel estimation for MIMO-OFDM systems publication-title: arXiv 2006 11796 – ident: ref18 doi: 10.1109/TIT.2007.892784 – ident: ref33 doi: 10.1109/GLOCOM.2007.829 – ident: ref26 doi: 10.1109/LWC.2020.3019321 – ident: ref34 doi: 10.1109/LWC.2019.2962114 – year: 2016 ident: ref43 article-title: TensorFlow: Large-scale machine learning on heterogeneous distributed systems publication-title: arXiv 1603 04467 – year: 2013 ident: ref20 article-title: Estimating or propagating gradients through stochastic neurons for conditional computation publication-title: arXiv 1308 3432 – ident: ref22 doi: 10.1109/JSAC.2008.081002 – ident: ref32 doi: 10.1109/TWC.2015.2455980 – year: 2015 ident: ref46 article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift publication-title: arXiv 1502 03167 – ident: ref30 doi: 10.1109/LCOMM.2020.2983018 – ident: ref37 doi: 10.1109/LCOMM.2018.2882829 – ident: ref8 doi: 10.1109/MCOM.2016.7402270 – ident: ref41 doi: 10.1109/JSTSP.2016.2520912 – ident: ref4 doi: 10.1109/ICASSP40776.2020.9054488 – ident: ref40 doi: 10.1109/TIT.2010.2046225 – ident: ref25 doi: 10.1109/WCNC.2012.6214417 – ident: ref36 doi: 10.1109/LWC.2018.2818160 – ident: ref15 doi: 10.1109/JSAIT.2020.2986467 – ident: ref9 doi: 10.1109/MCOM.2011.5783993
SSID	ssj0017655
Score	2.673436
Snippet	This paper shows that deep neural network (DNN) can be used for efficient and distributed channel estimation, quantization, feedback, and downlink multiuser...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	4044
SubjectTerms	Artificial neural networks Channel estimation Deep learning deep neural network (DNN) distributed source coding (DSC) Downlink downlink precoding Estimation Feedback feedback frequency-division duplex (FDD) Frequency division duplexing Machine learning massive multiple-input multiple-output (MIMO) Precoding quantization Quantization (signal) Radio equipment Robust design Training
Title	Deep Learning for Distributed Channel Feedback and Multiuser Precoding in FDD Massive MIMO
URI	https://ieeexplore.ieee.org/document/9347820 https://www.proquest.com/docview/2549755573
Volume	20
WOSCitedRecordID	wos000671527500002&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: 1558-2248 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0017655 issn: 1536-1276 databaseCode: RIE dateStart: 20020101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDLY2xAEOvAZivJQDFyS6jSZtmiPamOCwscMQE5eqSV00MXXTGPx-4rSrkEBI3HpIqtaOYzuOvw_gkkeZ0txoz3o_7QllhJfYRMjrZIE2OksI0MSRTcjhMJpM1KgG11UvDCK6y2fYokdXy0_n5oOOytqKC4J3q0NdSln0alUVAxk6hlNrwMQrI6uSZEe1x89dmwj6Ny1Ct_LLA5S1C3KcKj82Yudd-rv_-6492CmjSHZbqH0fapgfwPY3bMEGvPQQF6yET31lNjZlPQLJJX4rTBl1FeQ4Y33rvXRi3liSp8x149KxBRtRokxujU1z1u_12MAG2XZjZIOHweMhPPXvxt17ryRS8AwP5MpDxZVJJBofQxMGJkIuVMr9jCep1sYKKfO5wE6YaCFlYCM4ae3SRAKFxCjR_Ag28nmOx8BCxQPr4LQ1dCOUDnSWYiZMZJPRjBhvmtBeyzY2Jco4kV3MYpdtdFRstRGTNuJSG024qmYsCoSNP8Y2SPrVuFLwTThbqy8uTfA9pszX_ksg-cnvs05hi95d3L09g43V8gPPYdN8rqbvywu3ur4AoPDLNA
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDLZ4ScCB10AMBuTABYluXZM2zRFtTCC2wWGIiUvVpC5CoIJg8PuJs65CAiFx6yFRWzuO7Tj-PoBjHudKc6M96_20J5QRXmoTIc_PQ210nhKgiSObkMNhPB6rmzk4rXphENFdPsMmPbpafvZiPuiorKW4IHi3eVgMhQja026tqmYgI8dxak2YmGVkVZT0VWt017GpYNBuEr5VUB6hzJyQY1X5sRU7_9Jb_9-XbcBaGUeys6niN2EOiy1Y_YYuWIP7LuIrKwFUH5iNTlmXYHKJ4QozRn0FBT6znvVfOjVPLC0y5vpx6eCC3VCqTI6NPRas1-2ygQ2z7dbIBpeD62247Z2POhdeSaXgGR7KiYeKK5NKNAFGJgpNjFyojAc5TzOtjRVSHnCBfpRqIWVoYzhpLdPEAoXEONV8BxaKlwJ3gUWKh9bFaWvqRigd6jzDXJjYpqM5cd7UoTWTbWJKnHGiu3hOXL7hq8RqIyFtJKU26nBSzXidYmz8MbZG0q_GlYKvQ2OmvqQ0wveEcl_7L6Hke7_POoLli9Ggn_Qvh1f7sELvmd7EbcDC5O0DD2DJfE4e398O3Ur7Al7bzns
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=Deep+Learning+for+Distributed+Channel+Feedback+and+Multiuser+Precoding+in+FDD+Massive+MIMO&rft.jtitle=IEEE+transactions+on+wireless+communications&rft.au=Sohrabi%2C+Foad&rft.au=Attiah%2C+Kareem+M.&rft.au=Yu%2C+Wei&rft.date=2021-07-01&rft.issn=1536-1276&rft.eissn=1558-2248&rft.volume=20&rft.issue=7&rft.spage=4044&rft.epage=4057&rft_id=info:doi/10.1109%2FTWC.2021.3055202&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TWC_2021_3055202
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1536-1276&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1536-1276&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1536-1276&client=summon