Joint Coding-Modulation for Digital Semantic Communications via Variational Autoencoder

Semantic communications have emerged as a new paradigm for improving communication efficiency by transmitting the semantic information of a source message that is most relevant to a desired task at the receiver. Most existing approaches typically utilize neural networks (NNs) to design end-to-end se...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE transactions on communications Ročník 72; číslo 9; s. 5626 - 5640
Hlavní autori:	Bo, Yufei, Duan, Yiheng, Shao, Shuo, Tao, Meixia
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	New York IEEE 01.09.2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Artificial neural networks Coding Communication Communications systems Decoding Digital imaging Digital modulation Information theory Modulation mutual information Neural networks Probabilistic logic Receivers Semantic communications Semantics Symbols Transition probabilities variational autoencoder
ISSN:	0090-6778, 1558-0857
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Semantic communications have emerged as a new paradigm for improving communication efficiency by transmitting the semantic information of a source message that is most relevant to a desired task at the receiver. Most existing approaches typically utilize neural networks (NNs) to design end-to-end semantic communication systems, where NN-based semantic encoders output continuously distributed signals to be sent directly to the channel in an analog fashion. In this work, we propose a joint coding-modulation (JCM) framework for digital semantic communications by using variational autoencoder (VAE). Our approach learns the transition probability from source data to discrete constellation symbols, thereby avoiding the non-differentiability problem of digital modulation. Meanwhile, by jointly designing the coding and modulation process together, we can match the obtained modulation strategy with the operating channel condition. We also derive a matching loss function with information-theoretic meaning for end-to-end training. Experiments on image semantic communication validate the superiority of our proposed JCM framework over the state-of-the-art quantization-based digital semantic coding-modulation methods across a wide range of channel conditions, transmission rates, and modulation orders. Furthermore, its performance gap to analog semantic communication reduces as the modulation order increases while enjoying the hardware implementation convenience.
AbstractList	Semantic communications have emerged as a new paradigm for improving communication efficiency by transmitting the semantic information of a source message that is most relevant to a desired task at the receiver. Most existing approaches typically utilize neural networks (NNs) to design end-to-end semantic communication systems, where NN-based semantic encoders output continuously distributed signals to be sent directly to the channel in an analog fashion. In this work, we propose a joint coding-modulation (JCM) framework for digital semantic communications by using variational autoencoder (VAE). Our approach learns the transition probability from source data to discrete constellation symbols, thereby avoiding the non-differentiability problem of digital modulation. Meanwhile, by jointly designing the coding and modulation process together, we can match the obtained modulation strategy with the operating channel condition. We also derive a matching loss function with information-theoretic meaning for end-to-end training. Experiments on image semantic communication validate the superiority of our proposed JCM framework over the state-of-the-art quantization-based digital semantic coding-modulation methods across a wide range of channel conditions, transmission rates, and modulation orders. Furthermore, its performance gap to analog semantic communication reduces as the modulation order increases while enjoying the hardware implementation convenience.
Author	Bo, Yufei Duan, Yiheng Tao, Meixia Shao, Shuo
Author_xml	– sequence: 1 givenname: Yufei orcidid: 0009-0001-6880-8562 surname: Bo fullname: Bo, Yufei email: boyufei01@sjtu.edu.cn organization: Department of Electronic Engineering and the Cooperative Medianet Innovation Center (CMIC), Shanghai Jiao Tong University, Shanghai, China – sequence: 2 givenname: Yiheng surname: Duan fullname: Duan, Yiheng email: duanyiheng@sjtu.edu.cn organization: Department of Electronic Engineering and the Cooperative Medianet Innovation Center (CMIC), Shanghai Jiao Tong University, Shanghai, China – sequence: 3 givenname: Shuo orcidid: 0000-0003-2872-795X surname: Shao fullname: Shao, Shuo email: shuoshao@sjtu.edu.cn organization: School of Cyber Science and Engineering, Shanghai Jiao Tong University, Shanghai, China – sequence: 4 givenname: Meixia orcidid: 0000-0002-0799-0954 surname: Tao fullname: Tao, Meixia email: mxtao@sjtu.edu.cn organization: Department of Electronic Engineering and the Cooperative Medianet Innovation Center (CMIC), Shanghai Jiao Tong University, Shanghai, China
BookMark	eNp9kD1PwzAQhi0EEm3hDyCGSMwp59ixk7Eq32rVgQJj5MZO5Sqxi-0g8e9xPwbEwHQ63fOc7t4hOjXWKISuMIwxhvJ2OV3M5-MMMjompGA55ydogPO8SKHI-SkaAJSQMs6LczT0fgMAFAgZoI8Xq01IplZqs07nVvatCNqapLEuudNrHUSbvKpOmKDriHVdb3S9R3zypUXyLpzet5Gb9MEqU1up3AU6a0Tr1eWxjtDbw_1y-pTOFo_P08ksrbOShVRmkiumKBNZI5qM50WjMKslZStouFqxLHYcIJdUKeAijiXhJYdSlpiJmozQzWHv1tnPXvlQbWzv4jG-IhgYLYFyFqniQNXOeu9UU9Xxsd3VwQndVhiqXYzVPsZqF2N1jDGq2R9163Qn3Pf_0vVB0kqpXwItc0KA_ACkaYG7
CODEN	IECMBT
CitedBy_id	crossref_primary_10_1109_JIOT_2025_3565017 crossref_primary_10_1109_LWC_2025_3548084 crossref_primary_10_1109_JIOT_2025_3545667 crossref_primary_10_1109_JIOT_2025_3579582 crossref_primary_10_1109_JSAC_2025_3536557 crossref_primary_10_1109_LCOMM_2025_3571544 crossref_primary_10_1109_TGRS_2025_3576382 crossref_primary_10_1016_j_eng_2025_07_022 crossref_primary_10_1109_JIOT_2025_3530462 crossref_primary_10_1109_JSAC_2025_3531406 crossref_primary_10_1109_JIOT_2024_3516730 crossref_primary_10_1109_JIOT_2025_3534462 crossref_primary_10_3390_a17110492 crossref_primary_10_1016_j_comnet_2025_111531 crossref_primary_10_1109_TCCN_2024_3510586 crossref_primary_10_1109_JSAC_2025_3559138 crossref_primary_10_1109_JSAC_2025_3559149 crossref_primary_10_1109_LCOMM_2025_3587319 crossref_primary_10_1109_TCOMM_2024_3450877 crossref_primary_10_1145_3701701_3701707 crossref_primary_10_1109_TWC_2025_3543373 crossref_primary_10_3390_electronics14050956 crossref_primary_10_1364_OE_568127 crossref_primary_10_3390_electronics14061130
Cites_doi	10.1109/LWC.2021.3136045 10.48550/arXiv.1312.6114 10.1109/JSAC.2022.3221968 10.23919/JCIN.2021.9663101 10.1109/TSP.2021.3071210 10.1109/wcsp55476.2022.10039447 10.1109/JSAC.2021.3087240 10.1109/OJCOMS.2022.3189023 10.1109/LWC.2021.3132067 10.1109/GLOBECOM48099.2022.10001359 10.1109/TCCN.2019.2919300 10.1109/TCOMM.2022.3180997 10.1109/JSAIT.2022.3231042 10.1023/A:1020281327116 10.1016/j.dsp.2021.103134 10.1109/18.256499 10.1007/s11263-021-01491-7 10.1002/0471200611 10.1109/JSAC.2022.3223408 10.1109/tai.2022.3185179 10.1109/JSAC.2022.3180802 10.1109/GCWkshps45667.2019.9024567 10.1145/3422622 10.48550/ARXIV.1706.03762 10.1109/JSAC.2022.3221991 10.1109/ACCESS.2019.2920929 10.1109/JSAC.2022.3221999 10.1109/JSAC.2022.3221977 10.1109/JSAC.2020.3036968 10.1109/JSAC.2022.3191326 10.1080/01621459.2017.1285773 10.1109/GLOBECOM42002.2020.9348032 10.1109/MWC.101.2100269 10.1109/CVPR.2016.90 10.1109/JSAC.2021.3126087 10.1109/JSAC.2022.3221952 10.1109/ACCESS.2019.2897381
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID	97E RIA RIE AAYXX CITATION 7SP 8FD L7M
DOI	10.1109/TCOMM.2024.3386577
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library (IEL) 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	1558-0857
EndPage	5640
ExternalDocumentID	10_1109_TCOMM_2024_3386577 10495330
Genre	orig-research
GrantInformation_xml	– fundername: Natural Science Foundation of China grantid: 62125108; 62231022 funderid: 10.13039/501100001809 – fundername: Natural Science Foundation of China grantid: 12031011 funderid: 10.13039/501100001809 – fundername: National Key Research and Development Program of China grantid: 2020YFA0712300 – fundername: Fundamental Research Funds for the Central Universities; Fundamental Research Funds for the Central Universities of China funderid: 10.13039/501100012226
GroupedDBID	-~X .DC 0R~ 29I 3EH 4.4 5GY 5VS 6IK 85S 97E AAJGR AARMG AASAJ AAWTH ABAZT ABFSI ABQJQ ABVLG ACGFO ACGFS ACIWK ACKIV ACNCT AENEX 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 HZ~ H~9 IAAWW IBMZZ ICLAB IES IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P RIA RIE RNS TAE TN5 VH1 ZCA ZCG AAYXX CITATION 7SP 8FD L7M
ID	FETCH-LOGICAL-c296t-d2d7e6e46a2faf2758fe16cd46b0f7eb6216c7005d4ee07a8fed379709d916ac3
IEDL.DBID	RIE
ISICitedReferencesCount	37
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001319557300013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0090-6778
IngestDate	Mon Jun 30 10:12:42 EDT 2025 Sat Nov 29 04:08:28 EST 2025 Tue Nov 18 21:32:24 EST 2025 Wed Aug 27 01:59:20 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	9
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-c296t-d2d7e6e46a2faf2758fe16cd46b0f7eb6216c7005d4ee07a8fed379709d916ac3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0009-0001-6880-8562 0000-0002-0799-0954 0000-0003-2872-795X
PQID	3106490476
PQPubID	85472
PageCount	15
ParticipantIDs	ieee_primary_10495330 proquest_journals_3106490476 crossref_citationtrail_10_1109_TCOMM_2024_3386577 crossref_primary_10_1109_TCOMM_2024_3386577
PublicationCentury	2000
PublicationDate	2024-09-01
PublicationDateYYYYMMDD	2024-09-01
PublicationDate_xml	– month: 09 year: 2024 text: 2024-09-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on communications
PublicationTitleAbbrev	TCOMM
PublicationYear	2024
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 ref12 ref15 ref14 ref11 ref10 ref17 ref16 ref19 ref18 ref46 ref48 ref47 ref44 ref43 Mnih (ref39); 32 ref49 ref8 ref7 Mohamed (ref38) 2020; 21 ref9 ref4 ref3 Choi (ref37); 97 ref5 ref35 ref36 Le (ref45) 2015; 7 ref30 ref32 ref2 Jang (ref31) 2016 ref1 Gumbel (ref41) 1954 Barber (ref33) Krizhevsky (ref42) 2009 ref24 ref23 ref26 ref25 ref20 ref22 ref21 Linsker (ref29) Tishby (ref34) 2000 ref28 ref27 Gregor (ref40); 32 Qin (ref6) 2021
References_xml	– year: 2021 ident: ref6 article-title: Semantic communications: Principles and challenges publication-title: arXiv:2201.01389 – start-page: 1 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref33 article-title: Kernelized infomax clustering – ident: ref18 doi: 10.1109/LWC.2021.3136045 – ident: ref30 doi: 10.48550/arXiv.1312.6114 – ident: ref17 doi: 10.1109/JSAC.2022.3221968 – ident: ref4 doi: 10.23919/JCIN.2021.9663101 – ident: ref9 doi: 10.1109/TSP.2021.3071210 – ident: ref1 doi: 10.1109/wcsp55476.2022.10039447 – ident: ref7 doi: 10.1109/JSAC.2021.3087240 – year: 2000 ident: ref34 article-title: The information bottleneck method publication-title: arXiv:physics/0004057 – ident: ref11 doi: 10.1109/OJCOMS.2022.3189023 – ident: ref10 doi: 10.1109/LWC.2021.3132067 – ident: ref23 doi: 10.1109/GLOBECOM48099.2022.10001359 – ident: ref20 doi: 10.1109/TCCN.2019.2919300 – year: 2016 ident: ref31 article-title: Categorical reparameterization with Gumbel–Softmax publication-title: arXiv:1611.01144 – ident: ref28 doi: 10.1109/TCOMM.2022.3180997 – ident: ref27 doi: 10.1109/JSAIT.2022.3231042 – ident: ref36 doi: 10.1023/A:1020281327116 – ident: ref2 doi: 10.1016/j.dsp.2021.103134 – ident: ref46 doi: 10.1109/18.256499 – year: 2009 ident: ref42 article-title: Learning multiple layers of features from tiny images – ident: ref13 doi: 10.1007/s11263-021-01491-7 – ident: ref32 doi: 10.1002/0471200611 – ident: ref5 doi: 10.1109/JSAC.2022.3223408 – ident: ref44 doi: 10.1109/tai.2022.3185179 – start-page: 1 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref29 article-title: Towards an organizing principle for a layered perceptual network – ident: ref15 doi: 10.1109/JSAC.2022.3180802 – ident: ref48 doi: 10.1109/GCWkshps45667.2019.9024567 – ident: ref21 doi: 10.1145/3422622 – ident: ref19 doi: 10.48550/ARXIV.1706.03762 – volume: 7 start-page: 3 issue: 7 year: 2015 ident: ref45 article-title: Tiny imagenet visual recognition challenge publication-title: CS 231N – ident: ref14 doi: 10.1109/JSAC.2022.3221991 – volume-title: Statistical Theory of Extreme Values and Some Practical Applications: A Series of Lectures year: 1954 ident: ref41 – ident: ref25 doi: 10.1109/ACCESS.2019.2920929 – volume: 32 start-page: 1242 volume-title: Proc. 31st Int. Conf. Mach. Learn. ident: ref40 article-title: Deep autoregressive networks – volume: 32 start-page: 1791 volume-title: Proc. 31th Int. Conf. Mach. Learn. (ICML) ident: ref39 article-title: Neural variational inference and learning in belief networks – ident: ref22 doi: 10.1109/JSAC.2022.3221999 – ident: ref16 doi: 10.1109/JSAC.2022.3221977 – ident: ref24 doi: 10.1109/JSAC.2020.3036968 – ident: ref26 doi: 10.1109/JSAC.2022.3191326 – volume: 21 start-page: 5183 issue: 1 year: 2020 ident: ref38 article-title: Monte Carlo gradient estimation in machine learning publication-title: J. Mach. Learn. Res. – ident: ref35 doi: 10.1080/01621459.2017.1285773 – ident: ref49 doi: 10.1109/GLOBECOM42002.2020.9348032 – volume: 97 start-page: 1182 volume-title: Proc. Int. Conf. Mach. Learn. ident: ref37 article-title: Neural joint source-channel coding – ident: ref3 doi: 10.1109/MWC.101.2100269 – ident: ref43 doi: 10.1109/CVPR.2016.90 – ident: ref12 doi: 10.1109/JSAC.2021.3126087 – ident: ref8 doi: 10.1109/JSAC.2022.3221952 – ident: ref47 doi: 10.1109/ACCESS.2019.2897381
SSID	ssj0004033
Score	2.6698778
Snippet	Semantic communications have emerged as a new paradigm for improving communication efficiency by transmitting the semantic information of a source message that...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	5626
SubjectTerms	Artificial neural networks Coding Communication Communications systems Decoding Digital imaging Digital modulation Information theory Modulation mutual information Neural networks Probabilistic logic Receivers Semantic communications Semantics Symbols Transition probabilities variational autoencoder
Title	Joint Coding-Modulation for Digital Semantic Communications via Variational Autoencoder
URI	https://ieeexplore.ieee.org/document/10495330 https://www.proquest.com/docview/3106490476
Volume	72
WOSCitedRecordID	wos001319557300013&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: 1558-0857 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004033 issn: 0090-6778 databaseCode: RIE dateStart: 19720101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS8MwEA9OfNAHPyfOL_Lgm3S2aZY0j2M6RNwU_HwrbXKRgq6ydf79JmmmG6LgW0tzpdzlmrvkfvdD6ETmeayIjoI4I52ACqntIaEOtEo6oIXuZA4L83jNh8Pk-VncerC6w8IAgCs-g7a9dGf5qpRTu1VmPLyuhmygBue8Bmt9gyDD2LectPXsPJkhZEJxdt-7GQxMLkhoO7Ycl5wvrEKOVuXHv9gtMP2Nf37aJlr3kSTu1qbfQksw2kZrc_0Fd9DTVVmMKtwr7QIVDErlubqwiVTxefFiCUPwHbwZ7RYSL2BFJvijyPCjyaT9biHuTqvSdr1UMG6ih_7Ffe8y8EwKgSSCVYEiigMDyjKiM01MjqAhYlJRlofasqIQc8eNQyoKEPLMPFYxFzwUyoSPmYx30fKoHMEewokwcnGkIp4nFExornMFChinOWVEkRaKZppNpW8zbtkuXlOXboQiddZIrTVSb40WOv2Sea-bbPw5umn1PzeyVn0LHc4smHpHnKQmemVUhJSz_V_EDtCqfXtdN3aIlqvxFI7Qivyoisn42M2xTzfOz-k
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dT9swED8xmDR44GMDUT6GH_aGwhLHteNHVEDA2oK0wniLEvs8RRoNalP-fmzHHaCJSbwlik-J7nzxnX2_-wF8U2WZamqSKC1oN2JSGXdIaCKjsy4aabqFx8Lc9sVwmN3dyesAVvdYGET0xWd45C79Wb6u1cxtlVkPb6shP8BSlzGatHCtZxhknIamk66iXWRzjEwsv496V4OBzQYpO0ody6UQr9YhT6zyz9_YLzFna-_8uHVYDbEkOW6NvwELOP4MKy86DH6BX5d1NW5Ir3ZLVDSodWDrIjZWJSfVb0cZQn7ivdVvpcgrtMiUPFYFubW5dNgvJMezpnZ9LzVONuHm7HTUO48Cl0KkqORNpKkWyJHxgprCUJslGEy40oyXsXG8KNTeCeuSmiHGorCPdSqkiKW2AWSh0i1YHNdj3AaSSSuXJjoRZcbQBuem1KiRC1YyTjXtQDLXbK5Co3HHd_En9wlHLHNvjdxZIw_W6MDhX5mHts3Gf0dvOv2_GNmqvgN7cwvmwRWnuY1fOZMxE3znDbED-HQ-GvTz_sXwxy4suze1VWR7sNhMZrgPH9VjU00nX_18ewIxSdMw
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=Joint+Coding-Modulation+for+Digital+Semantic+Communications+via+Variational+Autoencoder&rft.jtitle=IEEE+transactions+on+communications&rft.au=Bo%2C+Yufei&rft.au=Duan%2C+Yiheng&rft.au=Shao%2C+Shuo&rft.au=Tao%2C+Meixia&rft.date=2024-09-01&rft.issn=0090-6778&rft.eissn=1558-0857&rft.volume=72&rft.issue=9&rft.spage=5626&rft.epage=5640&rft_id=info:doi/10.1109%2FTCOMM.2024.3386577&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TCOMM_2024_3386577
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0090-6778&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0090-6778&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0090-6778&client=summon