Robust Multidimensional Graph Neural Networks for Signal Processing in Wireless Communications With Edge-Graph Information Bottleneck

Signal processing is crucial for satisfying the high data rate requirements of future sixth-generation (6G) wireless networks. However, the rapid growth of wireless networks has brought about massive data traffic, which hinders the application of traditional optimization theory-based algorithms. Mea...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on signal processing Ročník 73; s. 2688 - 2703
Hlavní autoři: Liu, Ziheng, Zhang, Jiayi, Zhu, Yiyang, Shi, Enyu, Ai, Bo
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
ISSN:1053-587X, 1941-0476
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Signal processing is crucial for satisfying the high data rate requirements of future sixth-generation (6G) wireless networks. However, the rapid growth of wireless networks has brought about massive data traffic, which hinders the application of traditional optimization theory-based algorithms. Meanwhile, traditional graph neural networks (GNNs) focus on compressing inputs onto vertices to update representations, which often leads to their inability to effectively distinguish input features and severely weakens performance. In this context, designing efficient signal processing frameworks becomes imperative. Moreover, actual scenarios are susceptible to multipath interference and noise, resulting in specific differences between the received and actual information. To address these challenges, this paper incorporates multidimensional graph neural networks (MDGNNs) with edge-graph information bottleneck (EGIB) to design a robust framework for signal processing. Specifically, MDGNNs utilize hyper-edges instead of vertices to update representations to avoid indistinguishable features and reduce information loss, while EGIB encourages providing minimal sufficient information about outputs to avoid aggregation of irrelevant information. We numerically demonstrate that compared with existing frameworks, the proposed frameworks achieve excellent performance in terms of spectrum efficiency (SE) and complexity under multiple signal processing tasks. Remarkably, as the interference noise increases, the SE performance of the proposed frameworks gradually stabilizes. This reveals the proposed frameworks have excellent robustness in interference prone environments, especially in wireless policies related to channel matrices.
AbstractList Signal processing is crucial for satisfying the high data rate requirements of future sixth-generation (6G) wireless networks. However, the rapid growth of wireless networks has brought about massive data traffic, which hinders the application of traditional optimization theory-based algorithms. Meanwhile, traditional graph neural networks (GNNs) focus on compressing inputs onto vertices to update representations, which often leads to their inability to effectively distinguish input features and severely weakens performance. In this context, designing efficient signal processing frameworks becomes imperative. Moreover, actual scenarios are susceptible to multipath interference and noise, resulting in specific differences between the received and actual information. To address these challenges, this paper incorporates multidimensional graph neural networks (MDGNNs) with edge-graph information bottleneck (EGIB) to design a robust framework for signal processing. Specifically, MDGNNs utilize hyper-edges instead of vertices to update representations to avoid indistinguishable features and reduce information loss, while EGIB encourages providing minimal sufficient information about outputs to avoid aggregation of irrelevant information. We numerically demonstrate that compared with existing frameworks, the proposed frameworks achieve excellent performance in terms of spectrum efficiency (SE) and complexity under multiple signal processing tasks. Remarkably, as the interference noise increases, the SE performance of the proposed frameworks gradually stabilizes. This reveals the proposed frameworks have excellent robustness in interference prone environments, especially in wireless policies related to channel matrices.
Author Zhang, Jiayi
Zhu, Yiyang
Liu, Ziheng
Shi, Enyu
Ai, Bo
Author_xml – sequence: 1
  givenname: Ziheng
  orcidid: 0009-0000-5495-1619
  surname: Liu
  fullname: Liu, Ziheng
  email: zihengliu@bjtu.edu.cn
  organization: State Key Laboratory of Advanced Rail Autonomous Operation, School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China
– sequence: 2
  givenname: Jiayi
  orcidid: 0000-0003-2434-4329
  surname: Zhang
  fullname: Zhang, Jiayi
  email: jiayizhang@bjtu.edu.cn
  organization: State Key Laboratory of Advanced Rail Autonomous Operation, School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China
– sequence: 3
  givenname: Yiyang
  orcidid: 0009-0000-7641-7353
  surname: Zhu
  fullname: Zhu, Yiyang
  email: yiyangzhu@bjtu.edu.cn
  organization: State Key Laboratory of Advanced Rail Autonomous Operation, School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China
– sequence: 4
  givenname: Enyu
  orcidid: 0009-0007-9971-6066
  surname: Shi
  fullname: Shi, Enyu
  email: enyushi@bjtu.edu.cn
  organization: State Key Laboratory of Advanced Rail Autonomous Operation, School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China
– sequence: 5
  givenname: Bo
  orcidid: 0000-0001-6850-0595
  surname: Ai
  fullname: Ai, Bo
  email: boai@bjtu.edu.cn
  organization: State Key Laboratory of Advanced Rail Autonomous Operation, School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing, China
BookMark eNpFkEtP3DAUhS0EEq_uu2BhiXWm16_EWcKIl0QpKlTtLkqcm8GQ2IPtCPED-N_1dJC6uq9zPumeQ7LrvENCvjJYMAb1t8eH-wUHrhZCVRJA7ZADVktWgKzK3dyDEoXS1Z99chjjMwCTsi4PyMdP380x0e_zmGxvJ3TReteO9Cq06yd6h3PIwx2mNx9eIh18oA92tRHcB28wRutW1Dr62wYc80iXfppmZ02bMifmfXqiF_0Kiy3wxmXE9O9Iz31KIzo0L8dkb2jHiF8-6xH5dXnxuLwubn9c3SzPbgvDZZWKsgUYetOjUVpUlYCSIXDJJXItew1DNxjRKeS1bivRsb4U2nDVMZRao6rEETndctfBv84YU_Ps55C_iY3gsiw1q7nIKtiqTPAxBhyadbBTG94bBs0m7CaH3WzCbj7DzpaTrcUi4n85A6a0VOIvpBl_LQ
CODEN ITPRED
Cites_doi 10.1109/TMLCN.2024.3354872
10.1109/ITW.2015.7133169
10.1109/MCOM.001.2200810
10.1109/TWC.2024.3478232
10.1109/TSP.2023.3244104
10.1109/JSAC.2021.3126087
10.1109/JSTSP.2023.3239189
10.1109/TPAMI.2023.3235931
10.1109/TSP.2018.2866382
10.1109/COMST.2023.3349276
10.1109/COMST.2023.3300664
10.1109/MWC.001.1900488
10.1109/TCOMM.2023.3269849
10.1109/TPAMI.2023.3337534
10.1109/TWC.2022.3219840
10.1109/TSP.2020.2988255
10.1109/TWC.2020.3033334
10.1109/TWC.2023.3305124
10.1109/LCOMM.2018.2825444
10.1109/JPROC.2024.3404491
10.1109/TWC.2024.3512663
10.1109/TWC.2021.3100133
10.1109/TWC.2015.2400437
10.1109/TCOMM.2019.2957482
10.1109/TWC.2023.3325735
10.1109/JSAC.2020.3000826
10.1609/aaai.v36i4.20335
10.1609/aaai.v38i8.28738
10.1007/s11432-020-2955-6
10.1109/MNET.001.1900287
10.1109/MWC.015.2300595
10.1109/TSP.2011.2147784
10.1109/TWC.2021.3069638
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2025
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/TSP.2025.3574005
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
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 1941-0476
EndPage 2703
ExternalDocumentID 10_1109_TSP_2025_3574005
11015845
Genre orig-research
GrantInformation_xml – fundername: Fundamental Research Funds for the Central Universities
  grantid: 2024YJS138
  funderid: 10.13039/501100012226
– fundername: National Natural Science Foundation of China
  grantid: 62471027
  funderid: 10.13039/501100001809
– fundername: National Natural Science Foundation of China
  grantid: 62221001
  funderid: 10.13039/501100001809
– fundername: ZTE Industry-University-Institute Cooperation Funds
  grantid: IA20250115003-PO0001; IA20240709018; IA20240319002
GroupedDBID -~X
.DC
0R~
29I
3EH
4.4
53G
5GY
5VS
6IK
85S
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABFSI
ABQJQ
ABVLG
ACGFO
ACIWK
ACKIV
ACNCT
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AJQPL
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ASUFR
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
E.L
EBS
EJD
F5P
HZ~
H~9
ICLAB
IFIPE
IFJZH
IPLJI
JAVBF
LAI
MS~
O9-
OCL
P2P
RIA
RIE
RNS
TAE
TN5
VH1
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c247t-6a00fdcdec583773061e02424e284d80fbfc3b5e298a73b1d638c25b1e488e573
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001534482200002&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1053-587X
IngestDate Sat Nov 01 15:20:07 EDT 2025
Sat Nov 29 07:39:01 EST 2025
Wed Aug 27 02:13:12 EDT 2025
IsPeerReviewed true
IsScholarly true
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-c247t-6a00fdcdec583773061e02424e284d80fbfc3b5e298a73b1d638c25b1e488e573
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0009-0000-7641-7353
0000-0001-6850-0595
0009-0007-9971-6066
0009-0000-5495-1619
0000-0003-2434-4329
PQID 3246681923
PQPubID 85478
PageCount 16
ParticipantIDs crossref_primary_10_1109_TSP_2025_3574005
ieee_primary_11015845
proquest_journals_3246681923
PublicationCentury 2000
PublicationDate 20250000
2025-00-00
20250101
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – year: 2025
  text: 20250000
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on signal processing
PublicationTitleAbbrev TSP
PublicationYear 2025
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
ref34
ref15
ref14
ref36
ref30
Tishby (ref31) 2000
ref11
ref33
ref10
ref32
Yu (ref37) 2021
ref2
ref1
ref17
ref16
ref38
ref19
ref18
Poole (ref39) 2019
Zhang (ref8) 2025
Xu (ref23) 2018
ref24
ref26
ref25
ref20
ref22
ref21
ref28
ref27
Wu (ref35) 2020; 33
ref29
ref7
ref9
ref4
ref3
ref6
ref5
References_xml – year: 2025
  ident: ref8
  article-title: Multi-agent reinforcement learning in wireless distributed networks for 6G
– ident: ref25
  doi: 10.1109/TMLCN.2024.3354872
– ident: ref32
  doi: 10.1109/ITW.2015.7133169
– ident: ref19
  doi: 10.1109/MCOM.001.2200810
– ident: ref28
  doi: 10.1109/TWC.2024.3478232
– ident: ref11
  doi: 10.1109/TSP.2023.3244104
– ident: ref33
  doi: 10.1109/JSAC.2021.3126087
– ident: ref9
  doi: 10.1109/JSTSP.2023.3239189
– ident: ref34
  doi: 10.1109/TPAMI.2023.3235931
– ident: ref15
  doi: 10.1109/TSP.2018.2866382
– start-page: 5171
  volume-title: Proc. ICML
  year: 2019
  ident: ref39
  article-title: On variational bounds of mutual information
– ident: ref4
  doi: 10.1109/COMST.2023.3349276
– ident: ref12
  doi: 10.1109/COMST.2023.3300664
– ident: ref7
  doi: 10.1109/MWC.001.1900488
– ident: ref14
  doi: 10.1109/TCOMM.2023.3269849
– volume: 33
  start-page: 20437
  year: 2020
  ident: ref35
  article-title: Graph information bottleneck
  publication-title: NeurIPS
– ident: ref36
  doi: 10.1109/TPAMI.2023.3337534
– ident: ref20
  doi: 10.1109/TWC.2022.3219840
– ident: ref29
  doi: 10.1109/TSP.2020.2988255
– ident: ref13
  doi: 10.1109/TWC.2020.3033334
– ident: ref24
  doi: 10.1109/TWC.2023.3305124
– ident: ref17
  doi: 10.1109/LCOMM.2018.2825444
– ident: ref1
  doi: 10.1109/JPROC.2024.3404491
– ident: ref27
  doi: 10.1109/TWC.2024.3512663
– volume-title: Proc. ICLR
  year: 2021
  ident: ref37
  article-title: Graph information bottleneck for subgraph recognition
– ident: ref26
  doi: 10.1109/TWC.2021.3100133
– ident: ref2
  doi: 10.1109/TWC.2015.2400437
– ident: ref16
  doi: 10.1109/TCOMM.2019.2957482
– ident: ref30
  doi: 10.1109/TWC.2023.3325735
– ident: ref3
  doi: 10.1109/JSAC.2020.3000826
– ident: ref38
  doi: 10.1609/aaai.v36i4.20335
– volume-title: Proc. ICLR
  year: 2018
  ident: ref23
  article-title: How powerful are graph neural networks?
– year: 2000
  ident: ref31
  article-title: The information bottleneck method
– ident: ref21
  doi: 10.1609/aaai.v38i8.28738
– ident: ref6
  doi: 10.1007/s11432-020-2955-6
– ident: ref5
  doi: 10.1109/MNET.001.1900287
– ident: ref22
  doi: 10.1109/MWC.015.2300595
– ident: ref10
  doi: 10.1109/TSP.2011.2147784
– ident: ref18
  doi: 10.1109/TWC.2021.3069638
SSID ssj0014496
Score 2.4673865
Snippet Signal processing is crucial for satisfying the high data rate requirements of future sixth-generation (6G) wireless networks. However, the rapid growth of...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Index Database
Publisher
StartPage 2688
SubjectTerms Apexes
Communications traffic
Edge-graph information bottleneck
Graph neural networks
Graph theory
Interference
multidimensional graph neural networks
Neural networks
Optimization
Representations
robust
Robustness
Signal processing
Signal processing algorithms
Silicon
Task complexity
Training
Wireless communication
Wireless communications
Wireless networks
Title Robust Multidimensional Graph Neural Networks for Signal Processing in Wireless Communications With Edge-Graph Information Bottleneck
URI https://ieeexplore.ieee.org/document/11015845
https://www.proquest.com/docview/3246681923
Volume 73
WOSCitedRecordID wos001534482200002&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: 1941-0476
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014496
  issn: 1053-587X
  databaseCode: RIE
  dateStart: 19910101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV27TsMwFLVoxQADzyIKBXlgYXDrPGwnI6AWpqqiReoWxY-UCpSiJuUP-G-unRSoEANbnNhW5Gv7Hj_OuQhdUSp97QtJAqYiErJYk9TjPlGcC5Vxk0oqXbAJMRxG02k8qsnqjgtjjHGXz0zXPrqzfL1QK7tV1gNX5YHDZA3UEIJXZK2vI4MwdMG4AC8EhEViuj6TpHFvMh7BStBn3YAJ6LNswwe5oCq_ZmLnXgb7__yxA7RX40h8Uxn-EG2Z_Ajt_lAXPEYfjwu5KkrsOLbaqvhXChz43opUYyvLAYlhdQ-8wIBe8Xg-sxlq9gDUguc5thdkXyGJN8gkBbwvn3FfzwypKqyZTfYjvl1YbeTcqJcWehr0J3cPpI66QJQfipLwlNJMK20Ug8UrTADcM9aRhwY8mY5oJjMVSGb8OEpFID0NI1j5THoG5gLDRHCCmvkiN6cIy8jK-QHEgnIA_NJY0YwKPwtTABVeELXR9doOyVslrpG4RQmNE7BZYm2W1DZro5Zt9-98dZO3UWdtuaQefkUCKJFzK_UWnP1R7Bzt2NqrzZQOapbLlblA2-q9nBfLS9ezPgEdkc17
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3JbtswEB1kKdD20KSpgzorD7nkQJuiRFE6JoXdBHGMoHYA3wRxkWs0kItI7h_0vzuk5KZB0ENuokRKAofkPC7vDcAZY4obLhUNhU5oJFJD8yDmVMex1EVsc8WUDzYhx-NkNkvvWrK658JYa_3hM9tzl34v3yz1yi2V9dFVBegwxSZsiyjirKFr_d00iCIfjgsRQ0hFImfrXUmW9qeTO5wLctELhcRWK555IR9W5cVY7B3McOeVv7YLH1okSS4a03-EDVvuwft_9AU_we9vS7WqauJZtsbp-DcaHOSrk6kmTpgDE-PmJHhFEL-SyWLuMrT8AXwLWZTEHZF9wCR5Riep8H79nQzM3NLmhS23yT0kl0unjlxa_aMD98PB9MsVbeMuUM0jWdM4Z6ww2lgtcPqKQ0AcWOfKI4u-zCSsUIUOlbA8TXIZqsBgH9ZcqMDiaGCFDPdhq1yW9jMQlThBPwRZWA6hX55qVjDJiyhHWBGESRfO13bIfjbyGpmflrA0Q5tlzmZZa7MudFy9P-Vrq7wLR2vLZW0HrDLEiXHsxN7Cg_8UO4W3V9PbUTa6Ht8cwjv3pWZp5Qi26seVPYY3-le9qB5PfCv7A_WR0MI
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=Robust+Multidimensional+Graph+Neural+Networks+for+Signal+Processing+in+Wireless+Communications+With+Edge-Graph+Information+Bottleneck&rft.jtitle=IEEE+transactions+on+signal+processing&rft.au=Liu%2C+Ziheng&rft.au=Zhang%2C+Jiayi&rft.au=Zhu%2C+Yiyang&rft.au=Shi%2C+Enyu&rft.date=2025&rft.issn=1053-587X&rft.eissn=1941-0476&rft.volume=73&rft.spage=2688&rft.epage=2703&rft_id=info:doi/10.1109%2FTSP.2025.3574005&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TSP_2025_3574005
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1053-587X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1053-587X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1053-587X&client=summon