Coding for Gaussian Two-Way Channels: Linear and Learning-Based Approaches

Although user cooperation cannot improve the capacity of Gaussian two-way channels (GTWCs) with independent noises, it can improve communication reliability. In this work, we aim to enhance and balance the communication reliability in GTWCs by minimizing the sum of error probabilities via joint desi...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on information theory Vol. 71; no. 7; pp. 4976 - 5012
Main Authors:	Kim, Junghoon, Kim, Taejoon, Das, Anindya Bijoy, Hosseinalipour, Seyyedali, Love, David J., Brinton, Christopher G.
Format:	Journal Article
Language:	English
Published:	IEEE 01.07.2025
Subjects:	Codes communication reliability Couplings Electronic mail Encoding Error probability Gaussian two-way channels linear coding neural coding Noise Power control Receivers Reliability Symbols user cooperation
ISSN:	0018-9448, 1557-9654
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Although user cooperation cannot improve the capacity of Gaussian two-way channels (GTWCs) with independent noises, it can improve communication reliability. In this work, we aim to enhance and balance the communication reliability in GTWCs by minimizing the sum of error probabilities via joint design of encoders and decoders at the users. We first formulate general encoding/decoding functions, where the user cooperation is captured by the coupling of user encoding processes. The coupling effect renders the encoder/decoder design non-trivial, requiring effective decoding to capture this effect, as well as efficient power management at the encoders within power constraints. To address these challenges, we propose two different two-way coding strategies: linear coding and learning-based coding. For linear coding, we propose optimal linear decoding and discuss new insights on encoding regarding user cooperation to balance reliability. We then propose an efficient algorithm for joint encoder/decoder design. For learning-based coding, we introduce a novel recurrent neural network (RNN)-based coding architecture, where we propose interactive RNNs and a power control layer for encoding, and we incorporate bi-directional RNNs with an attention mechanism for decoding. Through simulations, we show that our two-way coding methodologies outperform conventional channel coding schemes (that do not utilize user cooperation) significantly in sum-error performance. We also demonstrate that our linear coding excels at high signal-to-noise ratios (SNRs), while our RNN-based coding performs best at low SNRs. We further investigate our two-way coding strategies in terms of power distribution, two-way coding benefit, different coding rates, and block-length gain.
AbstractList	Although user cooperation cannot improve the capacity of Gaussian two-way channels (GTWCs) with independent noises, it can improve communication reliability. In this work, we aim to enhance and balance the communication reliability in GTWCs by minimizing the sum of error probabilities via joint design of encoders and decoders at the users. We first formulate general encoding/decoding functions, where the user cooperation is captured by the coupling of user encoding processes. The coupling effect renders the encoder/decoder design non-trivial, requiring effective decoding to capture this effect, as well as efficient power management at the encoders within power constraints. To address these challenges, we propose two different two-way coding strategies: linear coding and learning-based coding. For linear coding, we propose optimal linear decoding and discuss new insights on encoding regarding user cooperation to balance reliability. We then propose an efficient algorithm for joint encoder/decoder design. For learning-based coding, we introduce a novel recurrent neural network (RNN)-based coding architecture, where we propose interactive RNNs and a power control layer for encoding, and we incorporate bi-directional RNNs with an attention mechanism for decoding. Through simulations, we show that our two-way coding methodologies outperform conventional channel coding schemes (that do not utilize user cooperation) significantly in sum-error performance. We also demonstrate that our linear coding excels at high signal-to-noise ratios (SNRs), while our RNN-based coding performs best at low SNRs. We further investigate our two-way coding strategies in terms of power distribution, two-way coding benefit, different coding rates, and block-length gain.
Author	Kim, Taejoon Das, Anindya Bijoy Love, David J. Kim, Junghoon Hosseinalipour, Seyyedali Brinton, Christopher G.
Author_xml	– sequence: 1 givenname: Junghoon orcidid: 0000-0002-6900-6772 surname: Kim fullname: Kim, Junghoon email: junghoon@motorola.com organization: Department of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA – sequence: 2 givenname: Taejoon orcidid: 0000-0002-4017-9530 surname: Kim fullname: Kim, Taejoon email: taejoonkim@asu.edu organization: Motorola Mobility LLC, Chicago, IL, USA – sequence: 3 givenname: Anindya Bijoy orcidid: 0000-0002-3615-7400 surname: Das fullname: Das, Anindya Bijoy email: adas@uakron.edu organization: School of Electrical, Computer and Energy Engineering, Arizona State University, Tempe, AZ, USA – sequence: 4 givenname: Seyyedali orcidid: 0000-0003-4266-4000 surname: Hosseinalipour fullname: Hosseinalipour, Seyyedali email: alipour@buffalo.edu organization: Department of Electrical and Computer Engineering, The University of Akron, Akron, OH, USA – sequence: 5 givenname: David J. orcidid: 0000-0001-5922-4787 surname: Love fullname: Love, David J. email: djlove@purdue.edu organization: Department of Electrical Engineering, University at Buffalo-SUNY, Buffalo, NY, USA – sequence: 6 givenname: Christopher G. orcidid: 0000-0003-2771-3521 surname: Brinton fullname: Brinton, Christopher G. email: cgb@purdue.edu organization: Department of Electrical Engineering, University at Buffalo-SUNY, Buffalo, NY, USA
BookMark	eNp9kD1PwzAQhi1UJNrCzsDgP5Dij9iO2UoEpSgSSxBjdLEdalScyg5C_fekagfEwHR3w3Ov3meGJqEPDqFrShaUEn1br-sFI0wsuJCSs_wMTakQKtNS5BM0JYQWmc7z4gLNUvoYz1xQNkXPZW99eMddH_EKvlLyEHD93WdvsMflBkJw23SHKx8cRAzB4mpcwohk95CcxcvdLvZgNi5dovMOtsldneYcvT4-1OVTVr2s1uWyygyTcsha7qxVlGrSGq1oLm0OTtlWF6YzxAEzRAKMHVpRAOlAUsWU4dw6ZoEC43NEjn9N7FOKrmt20X9C3DeUNAcXzeiiObhoTi5GRP5BjB9g8H0YIvjtf-DNEfTOuV85uqCKC_4D2QVuPQ
CODEN	IETTAW
CitedBy_id	crossref_primary_10_1109_LCOMM_2025_3588133
Cites_doi	10.1109/26.539767 10.1109/TIT.2024.3426509 10.1109/Allerton49937.2022.9929416 10.1109/TIT.2017.2648821 10.1007/978-0-85729-652-8_1 10.1109/TIT.2023.3260807 10.1023/A:1008316327038 10.1109/TIT.1969.1054302 10.1109/JSAIT.2020.2986752 10.1017/CBO9780511807213 10.1007/s00158-009-0460-7 10.1109/JPROC.2015.2497203 10.1109/TCOM.1986.1096498 10.1109/TIT.1966.1053879 10.1109/TAC.2004.834119 10.1109/TIT.2021.3066855 10.1109/JSAIT.2022.3223901 10.1109/COMST.2015.2403614 10.1109/TIT.2010.2043769 10.1109/ICNN.1993.298725 10.1109/TIT.1982.1056454 10.1109/TIT.2011.2165796 10.1109/Allerton.2011.6120278 10.1109/TIT.1984.1056847
ContentType	Journal Article
DBID	97E RIA RIE AAYXX CITATION
DOI	10.1109/TIT.2025.3566324
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef
DatabaseTitle	CrossRef
DatabaseTitleList
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	1557-9654
EndPage	5012
ExternalDocumentID	10_1109_TIT_2025_3566324 10981735
Genre	orig-research
GrantInformation_xml	– fundername: NSF and Office of the Under Secretary of Defense (OUSD)–Research and Engineering, as part of the NSF Convergence Accelerator Track G: Securely Operating Through 5G Infrastructure Program grantid: ITE2515378 – fundername: NSF grantid: ITE2226447; CNS2514415; CNS2451268; EEC1941529; CNS2146171 – fundername: the Office of Naval Research (ONR) grantid: N000142112472
GroupedDBID	-~X .DC 0R~ 29I 3EH 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABFSI ABQJQ ABVLG ACGFO ACGFS ACGOD ACIWK AENEX AETEA AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ H~9 IAAWW IBMZZ ICLAB IDIHD IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS RXW TAE TN5 VH1 VJK AAYXX CITATION
ID	FETCH-LOGICAL-c266t-b3edd71190bc97146d4ae7db98cfc0ea2c06aa663b58a0fa61727c33de2da1a23
IEDL.DBID	RIE
ISICitedReferencesCount	0
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001513211100021&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0018-9448
IngestDate	Sat Nov 29 07:49:54 EST 2025 Tue Nov 18 22:53:27 EST 2025 Wed Aug 27 01:46:03 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-c266t-b3edd71190bc97146d4ae7db98cfc0ea2c06aa663b58a0fa61727c33de2da1a23
ORCID	0000-0003-2771-3521 0000-0002-4017-9530 0000-0003-4266-4000 0000-0002-6900-6772 0000-0001-5922-4787 0000-0002-3615-7400
PageCount	37
ParticipantIDs	ieee_primary_10981735 crossref_citationtrail_10_1109_TIT_2025_3566324 crossref_primary_10_1109_TIT_2025_3566324
PublicationCentury	2000
PublicationDate	2025-07-01
PublicationDateYYYYMMDD	2025-07-01
PublicationDate_xml	– month: 07 year: 2025 text: 2025-07-01 day: 01
PublicationDecade	2020
PublicationTitle	IEEE transactions on information theory
PublicationTitleAbbrev	TIT
PublicationYear	2025
Publisher	IEEE
Publisher_xml	– name: IEEE
References	ref13 ref35 ref12 Proakis (ref19) 2008 ref34 ref15 ref14 ref30 ref11 ref33 Shannon (ref4) ref10 ref32 Vasal (ref7) 2021 Bahdanau (ref29) 2014 ref2 ref1 ref17 Kim (ref18) Billingsley (ref36) 2012 ref23 ref20 Goodfellow (ref27) 2016 ref22 (ref24) 2021 ref21 (ref31) 2010 Ferziger (ref26) 1998 ref28 ref8 ref9 ref3 ref6 ref5 Chong (ref25) 2013; 75 Robert Safavi (ref16) 2021
References_xml	– ident: ref34 doi: 10.1109/26.539767 – year: 2021 ident: ref7 article-title: A dynamic program for linear sequential coding for two way Gaussian channel – ident: ref33 doi: 10.1109/TIT.2024.3426509 – volume-title: Digital Communications year: 2008 ident: ref19 – ident: ref1 doi: 10.1109/Allerton49937.2022.9929416 – ident: ref14 doi: 10.1109/TIT.2017.2648821 – ident: ref21 doi: 10.1007/978-0-85729-652-8_1 – ident: ref13 doi: 10.1109/TIT.2023.3260807 – volume: 75 volume-title: An Introduction to Optimization year: 2013 ident: ref25 – ident: ref23 doi: 10.1023/A:1008316327038 – ident: ref9 doi: 10.1109/TIT.1969.1054302 – ident: ref15 doi: 10.1109/JSAIT.2020.2986752 – ident: ref20 doi: 10.1017/CBO9780511807213 – start-page: 611 volume-title: Proc. 4th Berkeley Symp. Math. Statist. Probab. ident: ref4 article-title: Two-way communication channels – ident: ref22 doi: 10.1007/s00158-009-0460-7 – year: 2014 ident: ref29 article-title: Neural machine translation by jointly learning to align and translate publication-title: arXiv:1409.0473 – ident: ref2 doi: 10.1109/JPROC.2015.2497203 – ident: ref30 doi: 10.1109/TCOM.1986.1096498 – ident: ref8 doi: 10.1109/TIT.1966.1053879 – ident: ref12 doi: 10.1109/TAC.2004.834119 – volume-title: MATLAB Optimization Toolbox year: 2021 ident: ref24 – start-page: 16599 volume-title: Proc. Int. Conf. Mach. Learn. (ICML) ident: ref18 article-title: Robust non-linear feedback coding via power-constrained deep learning – ident: ref6 doi: 10.1109/TIT.2021.3066855 – ident: ref17 doi: 10.1109/JSAIT.2022.3223901 – ident: ref3 doi: 10.1109/COMST.2015.2403614 – ident: ref32 doi: 10.1109/TIT.2010.2043769 – volume-title: Probability and Measure year: 2012 ident: ref36 – year: 2021 ident: ref16 article-title: Deep extended feedback codes publication-title: arXiv:2105.01365 – ident: ref28 doi: 10.1109/ICNN.1993.298725 – volume-title: LTE: Evolved Universal Terrestrial Radio Access (E-UTRA): Multiplexing and Channel Coding year: 2010 ident: ref31 – ident: ref35 doi: 10.1109/TIT.1982.1056454 – ident: ref10 doi: 10.1109/TIT.2011.2165796 – ident: ref11 doi: 10.1109/Allerton.2011.6120278 – volume-title: Numerical Methods for Engineering Application year: 1998 ident: ref26 – volume-title: Deep Learning year: 2016 ident: ref27 – ident: ref5 doi: 10.1109/TIT.1984.1056847
SSID	ssj0014512
Score	2.4879825
Snippet	Although user cooperation cannot improve the capacity of Gaussian two-way channels (GTWCs) with independent noises, it can improve communication reliability....
SourceID	crossref ieee
SourceType	Enrichment Source Index Database Publisher
StartPage	4976
SubjectTerms	Codes communication reliability Couplings Electronic mail Encoding Error probability Gaussian two-way channels linear coding neural coding Noise Power control Receivers Reliability Symbols user cooperation
Title	Coding for Gaussian Two-Way Channels: Linear and Learning-Based Approaches
URI	https://ieeexplore.ieee.org/document/10981735
Volume	71
WOSCitedRecordID	wos001513211100021&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: 1557-9654 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014512 issn: 0018-9448 databaseCode: RIE dateStart: 19630101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELagYoCBQimivOSBhcFtEjtxwlYqymOoGIroFl1sByGhBPUB4t9zdtKqDCCxRZEtRffd-bvL-e4IuZBxxhMIEQHpayZUELLM08BMhMoj89DztHbDJuRoFE8myWNdrO5qYYwx7vKZ6dpHl8vXpVrYX2Vo4UnsSx5ukk0po6pYa5UyEKFftQb30YIx6FjmJL2kN74fYyQYhF2OzgsPxA8OWhuq4jhl2Pzn1-yR3dp5pP0K7X2yYYoWaS4HM9DaTltkZ63L4AF5GJSWoCi6p_QWFjNbNknHnyV7hi9qqwsK5McrilEpaj2FQtO66eoLu0aO07Rf9x03szZ5Gt6MB3esHqHAFDLvnGXcaC19ZP1MJRJPRS3ASJ0lscqVZyBQXgSAQsnCGLwcnD-jONcm0OBDwA9JoygLc0SoDwLRjtDliLnIFEAOhke54MIEKlKyQ3pLoaaq7i9ux1y8pS7O8JIUYUgtDGkNQ4dcrna8V701_ljbtgisrauEf_zL-xOybbdXF2tPSWM-XZgzsqU-5q-z6bnTnG_2L8Bo
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDLZ4ScCB5xBvcuDCoZA2adNyG4jxnjgUwa1ykxQhoQ6xDcS_x2k7NA4gcauqpKr82f3sOrYB9lWciwRDQkD5xpM6CL2cG_RsRMqjipBzY6phE6rbjR8fk7umWL2qhbHWVofP7KG7rHL5pqeH7lcZWXgS-0qEkzAdShnwulzrO2kgQ79uDu6TDVPYMcpK8uQovUwpFgzCQ0HuiwjkDxYaG6tSsUpn8Z_vswQLjfvI2jXeyzBhyxVYHI1mYI2lrsD8WJ_BVbg67TmKYuSgsnMc9l3hJEs_et4DfjJXX1ASQx4ziktJ7xmWhjVtV5-8E2I5w9pN53Hbb8F95yw9vfCaIQqeJu4deLmwxiifeD_XiaLvopFolcmTWBeaWww0jxBJKHkYIy-w8mi0EMYGBn0MxBpMlb3SrgPzURLeETkdsZC5RizQiqiQQtpAR1ptwNFIqJluOoy7QRcvWRVp8CQjGDIHQ9bAsAEH3zte6-4af6xtOQTG1tXC3_zl_h7MXqS3N9nNZfd6C-bco-pjttswNXgb2h2Y0e-D5_7bbqVFXyTSw68
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=Coding+for+Gaussian+Two-Way+Channels%3A+Linear+and+Learning-Based+Approaches&rft.jtitle=IEEE+transactions+on+information+theory&rft.au=Kim%2C+Junghoon&rft.au=Kim%2C+Taejoon&rft.au=Das%2C+Anindya+Bijoy&rft.au=Hosseinalipour%2C+Seyyedali&rft.date=2025-07-01&rft.issn=0018-9448&rft.eissn=1557-9654&rft.volume=71&rft.issue=7&rft.spage=4976&rft.epage=5012&rft_id=info:doi/10.1109%2FTIT.2025.3566324&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TIT_2025_3566324
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9448&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9448&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9448&client=summon