DualGNN: Dual Graph Neural Network for Multimedia Recommendation

One of the important factors affecting micro-video recommender systems is to model the multi-modal user preference on the micro-video. Despite the remarkable performance of prior arts, they are still limited by fusing the user preference derived from different modalities in a unified manner, ignorin...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on multimedia Jg. 25; S. 1074 - 1084
Hauptverfasser: Wang, Qifan, Wei, Yinwei, Yin, Jianhua, Wu, Jianlong, Song, Xuemeng, Nie, Liqiang
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 2023
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
ISSN:1520-9210, 1941-0077
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract One of the important factors affecting micro-video recommender systems is to model the multi-modal user preference on the micro-video. Despite the remarkable performance of prior arts, they are still limited by fusing the user preference derived from different modalities in a unified manner, ignoring the users tend to place different emphasis on different modalities. Furthermore, modality-missing is ubiquity and unavoidable in the micro-video recommendation, some modalities information of micro-videos are lacked in many cases, which negatively affects the multi-modal fusion operations. To overcome these disadvantages, we propose a novel framework for the micro-video recommendation, dubbed Dual Graph Neural Network (DualGNN), upon the user-microvideo bipartite and user co-occurrence graphs, which leverages the correlation between users to collaboratively mine the particular fusion pattern for each user. Specifically, we first introduce a single-modal representation learning module, which performs graph operations on the user-microvideo graph in each modality to capture single-modal user preferences on different modalities. And then, we devise a multi-modal representation learning module to explicitly model the user's attentions over different modalities and inductively learn the multi-modal user preference. Finally, we propose a prediction module to rank the potential micro-videos for users. Extensive experiments on two public datasets demonstrate the significant superiority of our DualGNN over state-of-the-arts methods.
AbstractList One of the important factors affecting micro-video recommender systems is to model the multi-modal user preference on the micro-video. Despite the remarkable performance of prior arts, they are still limited by fusing the user preference derived from different modalities in a unified manner, ignoring the users tend to place different emphasis on different modalities. Furthermore, modality-missing is ubiquity and unavoidable in the micro-video recommendation, some modalities information of micro-videos are lacked in many cases, which negatively affects the multi-modal fusion operations. To overcome these disadvantages, we propose a novel framework for the micro-video recommendation, dubbed Dual Graph Neural Network (DualGNN), upon the user-microvideo bipartite and user co-occurrence graphs, which leverages the correlation between users to collaboratively mine the particular fusion pattern for each user. Specifically, we first introduce a single-modal representation learning module, which performs graph operations on the user-microvideo graph in each modality to capture single-modal user preferences on different modalities. And then, we devise a multi-modal representation learning module to explicitly model the user’s attentions over different modalities and inductively learn the multi-modal user preference. Finally, we propose a prediction module to rank the potential micro-videos for users. Extensive experiments on two public datasets demonstrate the significant superiority of our DualGNN over state-of-the-arts methods.
Author Song, Xuemeng
Wu, Jianlong
Wang, Qifan
Wei, Yinwei
Yin, Jianhua
Nie, Liqiang
Author_xml – sequence: 1
  givenname: Qifan
  orcidid: 0000-0002-1237-366X
  surname: Wang
  fullname: Wang, Qifan
  email: wqf@mail.sdu.edu.cn
  organization: College of Computer Science and Technology, Shandong University, Qingdao, China
– sequence: 2
  givenname: Yinwei
  orcidid: 0000-0003-1791-3159
  surname: Wei
  fullname: Wei, Yinwei
  email: weiyinwei@hotmail.com
  organization: School of Computing, National University of Singapore, Singapore
– sequence: 3
  givenname: Jianhua
  orcidid: 0000-0002-4611-2986
  surname: Yin
  fullname: Yin, Jianhua
  email: jhyin@sdu.edu.cn
  organization: College of Computer Science and Technology, Shandong University, Qingdao, China
– sequence: 4
  givenname: Jianlong
  orcidid: 0000-0003-0247-5221
  surname: Wu
  fullname: Wu, Jianlong
  email: jlwu1992@sdu.edu.cn
  organization: College of Computer Science and Technology, Shandong University, Qingdao, China
– sequence: 5
  givenname: Xuemeng
  orcidid: 0000-0002-5274-4197
  surname: Song
  fullname: Song, Xuemeng
  email: sxmustc@gmail.com
  organization: College of Computer Science and Technology, Shandong University, Qingdao, China
– sequence: 6
  givenname: Liqiang
  orcidid: 0000-0003-1476-0273
  surname: Nie
  fullname: Nie, Liqiang
  email: nieliqiang@gmail.com
  organization: College of Computer Science and Technology, Shandong University, Qingdao, China
BookMark eNp9kEFLw0AQhRepYFu9C14CnlNnNtlk15NStQptBKnnZbPZYGqSrZsE8d-7tcWDB2HgvYH5ZoY3IaPWtoaQc4QZIoir9Wo1o0BxFmHEqeBHZIwixhAgTUfeMwqhoAgnZNJ1GwCMGaRjcnM3qHqRZdfBzgQLp7ZvQWYG55vM9J_WvQeldcFqqPuqMUWlghejbdOYtlB9ZdtTclyqujNnB52S14f79fwxXD4vnua3y1BTgX2oY8ZTpaFUigkm8jwxORpRaM2x5AhcK2C8jJCXsTEmL1LFdKFVRD2kvE7J5X7v1tmPwXS93NjBtf6kpKkQnEWRrylJ9lPa2a5zppS66n_-7J2qaokgd2lJn5bcpSUPaXkQ_oBbVzXKff2HXOyRyj_8Oy6ShCaMRd9WeHdQ
CODEN ITMUF8
CitedBy_id crossref_primary_10_1016_j_inffus_2025_103168
crossref_primary_10_1109_TKDE_2024_3424268
crossref_primary_10_1109_TNSE_2024_3383440
crossref_primary_10_3390_systems13010057
crossref_primary_10_1007_s00521_025_11372_6
crossref_primary_10_1007_s10844_024_00848_x
crossref_primary_10_3390_app142210187
crossref_primary_10_1007_s11263_024_02128_1
crossref_primary_10_1109_TCSS_2024_3490801
crossref_primary_10_1109_ACCESS_2025_3573204
crossref_primary_10_1007_s10489_024_06038_0
crossref_primary_10_1016_j_knosys_2025_114020
crossref_primary_10_1016_j_knosys_2025_113496
crossref_primary_10_1371_journal_pone_0287927
crossref_primary_10_1109_TKDE_2024_3493374
crossref_primary_10_1038_s41598_025_96462_0
crossref_primary_10_1145_3711855
crossref_primary_10_1109_TKDE_2023_3309995
crossref_primary_10_1016_j_knosys_2025_113766
crossref_primary_10_1109_TMM_2024_3361729
crossref_primary_10_1016_j_knosys_2023_111340
crossref_primary_10_1109_TSC_2025_3556640
crossref_primary_10_1109_TMM_2024_3382889
crossref_primary_10_4018_JOEUC_368009
crossref_primary_10_1007_s10115_025_02536_w
crossref_primary_10_1007_s00530_024_01548_w
crossref_primary_10_1038_s41598_025_96458_w
crossref_primary_10_1109_TETCI_2024_3358190
crossref_primary_10_1145_3762665
crossref_primary_10_1007_s10115_024_02309_x
crossref_primary_10_1109_TBDATA_2024_3426355
crossref_primary_10_1016_j_eswa_2025_128929
crossref_primary_10_1016_j_knosys_2025_113035
crossref_primary_10_1109_TETCI_2024_3386774
crossref_primary_10_1109_TMM_2024_3384058
crossref_primary_10_1016_j_compeleceng_2024_109213
crossref_primary_10_1145_3662738
crossref_primary_10_1016_j_iot_2025_101769
crossref_primary_10_1109_TMM_2024_3369875
crossref_primary_10_1007_s11704_024_3939_x
crossref_primary_10_1145_3682075
crossref_primary_10_3390_e27010056
crossref_primary_10_1007_s10844_025_00946_4
crossref_primary_10_1088_2632_2153_ad66af
crossref_primary_10_1016_j_inffus_2023_101989
crossref_primary_10_1109_ACCESS_2022_3174212
crossref_primary_10_1016_j_ipm_2025_104075
crossref_primary_10_1145_3715876
crossref_primary_10_1007_s10115_025_02456_9
crossref_primary_10_1007_s44443_025_00026_1
crossref_primary_10_1109_TCSVT_2024_3416294
Cites_doi 10.1109/CVPR.2019.01028
10.1109/TCSVT.2019.2962216
10.1145/3442381.3449986
10.1145/3394171.3413556
10.3390/rs10010052
10.24963/ijcai.2019/592
10.1145/3394171.3414012
10.1145/3308558.3313513
10.1109/ICASSP.2017.7952132
10.1609/aaai.v34i01.5330
10.1145/2964284.2964307
10.1145/3343031.3350950
10.1109/TIP.2019.2923608
10.1609/aaai.v30i1.9973
10.1145/3331184.3331267
10.1109/ICME51207.2021.9428201
10.1016/j.ipm.2020.102277
10.1109/TIP.2020.3002083
10.1145/3240508.3240546
10.1109/TMM.2021.3088307
10.1109/ICIP.2019.8803025
10.1145/3394171.3413653
10.1145/3343031.3351034
10.1145/3447239
10.1109/TNNLS.2022.3163789
10.1109/CVPR.2016.90
10.1145/3397271.3401063
10.1109/ICME51207.2021.9428120
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023
DBID 97E
RIA
RIE
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
DOI 10.1109/TMM.2021.3138298
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 Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 1941-0077
EndPage 1084
ExternalDocumentID 10_1109_TMM_2021_3138298
9662655
Genre orig-research
GrantInformation_xml – fundername: Natural Science Foundation of Shandong Province; Shandong Provincial Natural Science Foundation
  grantid: ZR2019QF001
  funderid: 10.13039/501100007129
– fundername: National Natural Science Foundation of China
  grantid: 62172261; 61802231
  funderid: 10.13039/501100001809
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
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
HZ~
H~9
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNS
TN5
VH1
ZY4
AAYXX
CITATION
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c291t-c4587ac0faa5959bb6eb1e9dcc81f8108ca058f318f4eeebd7a5cdca32ac0aca3
IEDL.DBID RIE
ISICitedReferencesCount 100
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000970791100004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1520-9210
IngestDate Sun Jun 29 15:39:34 EDT 2025
Tue Nov 18 22:43:53 EST 2025
Sat Nov 29 03:10:08 EST 2025
Wed Aug 27 02:21:33 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-c291t-c4587ac0faa5959bb6eb1e9dcc81f8108ca058f318f4eeebd7a5cdca32ac0aca3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0003-1791-3159
0000-0003-0247-5221
0000-0003-1476-0273
0000-0002-1237-366X
0000-0002-5274-4197
0000-0002-4611-2986
PQID 2799853353
PQPubID 75737
PageCount 11
ParticipantIDs ieee_primary_9662655
crossref_citationtrail_10_1109_TMM_2021_3138298
proquest_journals_2799853353
crossref_primary_10_1109_TMM_2021_3138298
PublicationCentury 2000
PublicationDate 20230000
2023-00-00
20230101
PublicationDateYYYYMMDD 2023-01-01
PublicationDate_xml – year: 2023
  text: 20230000
PublicationDecade 2020
PublicationPlace Piscataway
PublicationPlace_xml – name: Piscataway
PublicationTitle IEEE transactions on multimedia
PublicationTitleAbbrev TMM
PublicationYear 2023
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
ref31
ref30
ref11
ref33
ref10
Glorot (ref34) 2010
Kingma (ref35) 2015
ref2
ref1
ref17
Couprie (ref24)
ref19
ref18
Rendle (ref29) 2009
Arora (ref32) 2016
Kipf (ref16) 2017
ref23
ref26
ref25
ref20
ref22
ref28
ref27
ref8
ref7
ref9
Berg (ref21) 2017
ref4
ref3
ref6
ref5
References_xml – ident: ref14
  doi: 10.1109/CVPR.2019.01028
– ident: ref15
  doi: 10.1109/TCSVT.2019.2962216
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Representations
  year: 2016
  ident: ref32
  article-title: A simple but tough-to-beat baseline for sentence embeddings
– ident: ref23
  doi: 10.1145/3442381.3449986
– ident: ref2
  doi: 10.1145/3394171.3413556
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Representations
  year: 2015
  ident: ref35
  article-title: Adam: A method for stochastic optimization
– ident: ref28
  doi: 10.3390/rs10010052
– ident: ref33
  doi: 10.24963/ijcai.2019/592
– ident: ref18
  doi: 10.1145/3394171.3414012
– ident: ref5
  doi: 10.1145/3308558.3313513
– ident: ref31
  doi: 10.1109/ICASSP.2017.7952132
– ident: ref8
  doi: 10.1609/aaai.v34i01.5330
– ident: ref7
  doi: 10.1145/2964284.2964307
– ident: ref10
  doi: 10.1145/3343031.3350950
– start-page: 452
  volume-title: Proc. Conf. Uncertainty Artif. Intell.
  year: 2009
  ident: ref29
  article-title: BPR: Bayesian personalized ranking from implicit feedback
– ident: ref26
  doi: 10.1109/TIP.2019.2923608
– ident: ref12
  doi: 10.1609/aaai.v30i1.9973
– ident: ref22
  doi: 10.1145/3331184.3331267
– ident: ref27
  doi: 10.1109/ICME51207.2021.9428201
– ident: ref11
  doi: 10.1016/j.ipm.2020.102277
– ident: ref20
  doi: 10.1109/TIP.2020.3002083
– ident: ref3
  doi: 10.1145/3240508.3240546
– ident: ref19
  doi: 10.1109/TMM.2021.3088307
– start-page: 249
  volume-title: Proc. Int. Conf. Artif. Intell. Statist.
  year: 2010
  ident: ref34
  article-title: Understanding the difficulty of training deep feedforward neural networks
– ident: ref24
  article-title: Indoor semantic segmentation using depth information
– ident: ref25
  doi: 10.1109/ICIP.2019.8803025
– start-page: 1
  volume-title: Proc. Int. Conf. Learn. Representations
  year: 2017
  ident: ref16
  article-title: Semi-supervised classification with graph convolutional networks
– ident: ref1
  doi: 10.1145/3394171.3413653
– ident: ref6
  doi: 10.1145/3343031.3351034
– ident: ref17
  doi: 10.1145/3447239
– start-page: 1
  volume-title: Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Mining
  year: 2017
  ident: ref21
  article-title: Graph convolutional matrix completion
– ident: ref4
  doi: 10.1109/TNNLS.2022.3163789
– ident: ref30
  doi: 10.1109/CVPR.2016.90
– ident: ref9
  doi: 10.1145/3397271.3401063
– ident: ref13
  doi: 10.1109/ICME51207.2021.9428120
SSID ssj0014507
Score 2.6710408
Snippet One of the important factors affecting micro-video recommender systems is to model the multi-modal user preference on the micro-video. Despite the remarkable...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1074
SubjectTerms Acoustics
graph neural network
Graph neural networks
Learning
Micro-video recommender systems
Modules
multi-modal fusion
Multimedia
Neural networks
Preferences
Recommender systems
Representation learning
Representations
Task analysis
Video
Videos
Visualization
Title DualGNN: Dual Graph Neural Network for Multimedia Recommendation
URI https://ieeexplore.ieee.org/document/9662655
https://www.proquest.com/docview/2799853353
Volume 25
WOSCitedRecordID wos000970791100004&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 Xplore
  customDbUrl:
  eissn: 1941-0077
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0014507
  issn: 1520-9210
  databaseCode: RIE
  dateStart: 19990101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDLbGxAEODDYQg4Fy4IJEWfrIknACARuXVRyGtFuVpqmENDa0B78fJ30IBELi1FSK1dauYzuO_QFcoFkREdPcS3OqvMjXqaf8wHgs49pXHJ18Qx3YBI9jMZ3K5wZc1bUwxhh3-Mxc26HL5WcLvbFbZX10zYMBY1uwxfmgqNWqMwYRc6XRaI6oJzGOqVKSVPYn4zEGgoGP8WkoAim-mSCHqfJjIXbWZdj633vtw17pRZK7QuwH0DDzNrQqhAZSKmwbdr-0G-zA7cNGzUZxfEPsgIxsr2piu3PgTVwcByfowxJXlOtKSoiNTt_w6QXy0iG8DB8n909eiaDg6UD6a09HTHClaa4Uk0ym6QCXZiMzrYWfC58KrSgTOep1HuFXpRlXTGdahQESKbweQXO-mJtjINT4JgjzjBmFBk3ntutM6OqwqUIdT7vQr5ia6LK9uEW5mCUuzKAyQTEkVgxJKYYuXNYU70VrjT_mdizb63klx7vQq-SWlLq3SgKOISR6sSw8-Z3qFHYsaHyxkdKD5nq5MWewrT_Wr6vlufutPgHxtMn-
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS8MwED_mFNQHp5vi_MyDL4J1adqsiU-Kuk10xYcJeytpmoKgU_bh3-8l7YaiCD41hRxt73q5u1zufgAnaFZEyHXkpTlVXujr1FM-Mx7PIu2rCJ18Qx3YRBTHYjiUjxU4W9TCGGPc4TNzbocul5-96ZndKmuha87anC_BMg9DRotqrUXOIOSuOBoNEvUkRjLzpCSVrUG_j6Eg8zFCDQST4psRcqgqP5ZiZ186tf-92SZslH4kuSoEvwUVM6pDbY7RQEqVrcP6l4aDDbi8mamXbhxfEDsgXdutmtj-HHgTFwfCCXqxxJXluqISYuPTV3x6gb20DU-d28F1zysxFDzNpD_1dMhFpDTNleKSyzRt4-JsZKa18HPhU6EV5SJHzc5D_Ko0ixTXmVYBQyKF1x2ojt5GZhcINb5hQZ5xo9Ck6dz2nQlcJTZVqOVpE1pzpia6bDBucS5eEhdoUJmgGBIrhqQUQxNOFxTvRXONP-Y2LNsX80qON-FgLrek1L5JwiIMItGP5cHe71THsNob9B-Sh7v4fh_WLIR8sa1yANXpeGYOYUV_TJ8n4yP3i30CnjDNRQ
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=DualGNN%3A+Dual+Graph+Neural+Network+for+Multimedia+Recommendation&rft.jtitle=IEEE+transactions+on+multimedia&rft.au=Wang%2C+Qifan&rft.au=Wei%2C+Yinwei&rft.au=Yin%2C+Jianhua&rft.au=Wu%2C+Jianlong&rft.date=2023&rft.issn=1520-9210&rft.eissn=1941-0077&rft.volume=25&rft.spage=1074&rft.epage=1084&rft_id=info:doi/10.1109%2FTMM.2021.3138298&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TMM_2021_3138298
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1520-9210&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1520-9210&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1520-9210&client=summon