Multi-Modal Self-Supervised Learning Algorithm-Based Product Recommendation

With the rise of e-commerce, personalized recommendation algorithms have received much attention in recent years. Meanwhile, multimodal recommendation algorithms have become the next competitive track of personalized recommendation. The current mainstream recommendation algorithms (e.g., NeuMF, NGCF...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on automation science and engineering Vol. 22; pp. 15371 - 15380
Main Authors: Gao, Li, Fan, Haiping, Chen, Qingkui, Yang, Heyu
Format: Journal Article
Language:English
Published: IEEE 2025
Subjects:
ISSN:1545-5955, 1558-3783
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract With the rise of e-commerce, personalized recommendation algorithms have received much attention in recent years. Meanwhile, multimodal recommendation algorithms have become the next competitive track of personalized recommendation. The current mainstream recommendation algorithms (e.g., NeuMF, NGCF) rely too much on empirical data and do not effectively utilize multimodal information to model user preferences, while there is the problem of sparsity of user preference data. Secondly, they are still limited to using the same weights to fuse the item features of different modalities, and have the problem of inaccurate recommendation. For this reason, this paper proposes Multi-Modal Self-Supervised Learning Algorithm Based Product Recommendation (MMSLRec). 1) Data augmentation by self-supervised adversarial perturbation generation learning is performed to supplement the missing interaction information of tailed products to solve the common data sparsity problem in product recommendation. 2) A multimodal representation learning module is introduced to capture deep features in image and text modalities using AlexNet and Bert, respectively, in order to avoid the recommendation accuracy degradation problem caused by insufficient data feature learning. 3) Learning the user's perceived strength in different modalities, using the user co-occurrence matrix to fuse the features and make recommendations. Experiments on Amazon-Electronics, Amazon-Clothing, and Amazon-Baby, with different degrees of data sparsity verify the effectiveness of our MMSLRec in solving the data sparsity problem and the multimodal user preference modeling problem, and compared to the state-of-the-art baseline recommendation model on the three datasets, the Recall@20 improved by 9.26%, 3.11% and 2.92%, respectively. Note to Practitioners-The motivation for this article arises from the requirement of efficient recommendation algorithms for e-commerce platforms. Mainstream recommendation algorithms are mainly based on sparse user item history interaction data for recommendation, which receives the limitation of data sparsity problem to a larger extent. Secondly, it is still limited to using the same weights to fuse the features of different modalities in the multimodal recommendation process. In this paper, we propose MMSLRec, which solves the data sparsity problem to a certain extent by using adversarial generative networks and fuse the features from different users using the user co-occurrence matrix. This method achieves better results in different applications.
AbstractList With the rise of e-commerce, personalized recommendation algorithms have received much attention in recent years. Meanwhile, multimodal recommendation algorithms have become the next competitive track of personalized recommendation. The current mainstream recommendation algorithms (e.g., NeuMF, NGCF) rely too much on empirical data and do not effectively utilize multimodal information to model user preferences, while there is the problem of sparsity of user preference data. Secondly, they are still limited to using the same weights to fuse the item features of different modalities, and have the problem of inaccurate recommendation. For this reason, this paper proposes Multi-Modal Self-Supervised Learning Algorithm Based Product Recommendation (MMSLRec). 1) Data augmentation by self-supervised adversarial perturbation generation learning is performed to supplement the missing interaction information of tailed products to solve the common data sparsity problem in product recommendation. 2) A multimodal representation learning module is introduced to capture deep features in image and text modalities using AlexNet and Bert, respectively, in order to avoid the recommendation accuracy degradation problem caused by insufficient data feature learning. 3) Learning the user's perceived strength in different modalities, using the user co-occurrence matrix to fuse the features and make recommendations. Experiments on Amazon-Electronics, Amazon-Clothing, and Amazon-Baby, with different degrees of data sparsity verify the effectiveness of our MMSLRec in solving the data sparsity problem and the multimodal user preference modeling problem, and compared to the state-of-the-art baseline recommendation model on the three datasets, the Recall@20 improved by 9.26%, 3.11% and 2.92%, respectively. Note to Practitioners-The motivation for this article arises from the requirement of efficient recommendation algorithms for e-commerce platforms. Mainstream recommendation algorithms are mainly based on sparse user item history interaction data for recommendation, which receives the limitation of data sparsity problem to a larger extent. Secondly, it is still limited to using the same weights to fuse the features of different modalities in the multimodal recommendation process. In this paper, we propose MMSLRec, which solves the data sparsity problem to a certain extent by using adversarial generative networks and fuse the features from different users using the user co-occurrence matrix. This method achieves better results in different applications.
Author Yang, Heyu
Fan, Haiping
Gao, Li
Chen, Qingkui
Author_xml – sequence: 1
  givenname: Li
  orcidid: 0000-0002-5762-184X
  surname: Gao
  fullname: Gao, Li
  email: gaoli@usst.edu.cn
  organization: School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, China
– sequence: 2
  givenname: Haiping
  surname: Fan
  fullname: Fan, Haiping
  organization: School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, China
– sequence: 3
  givenname: Qingkui
  surname: Chen
  fullname: Chen, Qingkui
  organization: School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, China
– sequence: 4
  givenname: Heyu
  surname: Yang
  fullname: Yang, Heyu
  organization: School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai, China
BookMark eNpNkMtKAzEYhYNUsK0-gOBiXiA1l_knybKWesEWxdb1kCb_1MjMRDJTwbfXoV24OgfOZfFNyKiNLRJyzdmMc2Zut_PNciaYgJmEQgtdnJExB9BUKi1Hg8-BggG4IJOu-2RM5NqwMXleH-o-0HX0ts42WFd0c_jC9B069NkKbWpDu8_m9T6m0H809M4OwWuK_uD67A1dbBpsve1DbC_JeWXrDq9OOiXv98vt4pGuXh6eFvMVdUKwnlouK68LsBI1VmC0Ry1V5VVhdswJbXMHuUahgSvPFENlYecVoC88N87KKeHHX5di1yWsyq8UGpt-Ss7KgUY50CgHGuWJxt_m5rgJiPivb4zMOZO_7uZedQ
CODEN ITASC7
Cites_doi 10.1109/ICDM.2019.00087
10.1145/3485447.3512104
10.1109/CVPR.2009.5206848
10.1016/j.compag.2020.105779
10.1109/ICoICT61617.2024.10698392
10.1145/3038912.3052569
10.1145/3477495.3532058
10.1145/3394171.3413556
10.1007/s10462-019-09744-1
10.1109/ACCESS.2020.3019464
10.1109/ICCC59590.2023.10507494
10.1109/ICASSP.2018.8462624
10.1109/TMM.2022.3187556
10.1145/2783258.2783273
10.1145/3308558.3313513
10.1007/978-3-030-01240-3_45
10.1145/3477495.3532027
10.1016/j.ins.2019.10.038
10.1109/TNNLS.2022.3154345
10.1145/3343031.3351034
10.1109/ACCESS.2024.3368868
10.1145/3404835.3462862
10.1145/3331184.3331267
10.1016/j.knosys.2019.06.019
10.1049/trit.2020.0031
10.1145/3469213.3470423
10.1109/TMM.2021.3111487
10.1145/3394171.3413653
10.1145/1864708.1864770
10.1145/3209978.3209981
10.1145/3596250
ContentType Journal Article
DBID 97E
RIA
RIE
AAYXX
CITATION
DOI 10.1109/TASE.2025.3568286
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
EISSN 1558-3783
EndPage 15380
ExternalDocumentID 10_1109_TASE_2025_3568286
10993410
Genre orig-research
GrantInformation_xml – fundername: Major Policy Advisory Research Project of the Shanghai Municipal People’s Government
  grantid: 2025-A-25
– fundername: National Social Sciences Foundation of China
  grantid: 22BTQ021
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
F5P
HZ~
H~9
IFIPE
IPLJI
JAVBF
LAI
M43
O9-
OCL
PQQKQ
RIA
RIE
RNS
AAYXX
CITATION
ID FETCH-LOGICAL-c220t-a13fd865a3e8ef598de837fd769b0c28a4c548e28517d070e7a5bd75ed6d19ca3
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001494111500010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1545-5955
IngestDate Sat Nov 29 07:53:52 EST 2025
Wed Aug 27 01:37:50 EDT 2025
IsPeerReviewed false
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-c220t-a13fd865a3e8ef598de837fd769b0c28a4c548e28517d070e7a5bd75ed6d19ca3
ORCID 0000-0002-5762-184X
PageCount 10
ParticipantIDs crossref_primary_10_1109_TASE_2025_3568286
ieee_primary_10993410
PublicationCentury 2000
PublicationDate 20250000
2025-00-00
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – year: 2025
  text: 20250000
PublicationDecade 2020
PublicationTitle IEEE transactions on automation science and engineering
PublicationTitleAbbrev TASE
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
References ref13
ref35
ref12
ref34
ref15
ref14
Devlin (ref28) 2018
ref36
Van Meteren (ref5)
ref11
ref33
ref10
ref32
ref2
Vincent (ref17) 2010; 11
ref1
ref39
ref16
ref38
ref19
ref18
Krizhevsky (ref27)
ref24
ref23
ref26
Gulrajani (ref31)
ref25
ref20
Ma (ref37)
ref22
Glorot (ref30)
ref21
ref29
ref8
ref7
ref4
Khosla (ref9); 33
ref3
ref6
References_xml – ident: ref2
  doi: 10.1109/ICDM.2019.00087
– ident: ref10
  doi: 10.1145/3485447.3512104
– ident: ref33
  doi: 10.1109/CVPR.2009.5206848
– ident: ref3
  doi: 10.1016/j.compag.2020.105779
– ident: ref6
  doi: 10.1109/ICoICT61617.2024.10698392
– ident: ref34
  doi: 10.1145/3038912.3052569
– ident: ref26
  doi: 10.1145/3477495.3532058
– ident: ref36
  doi: 10.1145/3394171.3413556
– ident: ref8
  doi: 10.1007/s10462-019-09744-1
– ident: ref20
  doi: 10.1109/ACCESS.2020.3019464
– ident: ref12
  doi: 10.1109/ICCC59590.2023.10507494
– start-page: 1
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref37
  article-title: Learning disentangled representations for recommendation
– ident: ref32
  doi: 10.1109/ICASSP.2018.8462624
– ident: ref38
  doi: 10.1109/TMM.2022.3187556
– start-page: 47
  volume-title: Proc. Mach. Learn. New Inf. Age, MLnet/ECML2000 Workshop
  ident: ref5
  article-title: Using content-based filtering for recommendation
– ident: ref16
  doi: 10.1145/2783258.2783273
– volume: 11
  start-page: 3371
  issue: 12
  year: 2010
  ident: ref17
  article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion
  publication-title: J. Mach. Learn. Res.
– ident: ref11
  doi: 10.1145/3308558.3313513
– ident: ref29
  doi: 10.1007/978-3-030-01240-3_45
– ident: ref39
  doi: 10.1145/3477495.3532027
– ident: ref15
  doi: 10.1016/j.ins.2019.10.038
– ident: ref22
  doi: 10.1109/TNNLS.2022.3154345
– volume: 33
  start-page: 18661
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref9
  article-title: Supervised contrastive learning
– ident: ref13
  doi: 10.1145/3343031.3351034
– ident: ref7
  doi: 10.1109/ACCESS.2024.3368868
– ident: ref25
  doi: 10.1145/3404835.3462862
– ident: ref35
  doi: 10.1145/3331184.3331267
– year: 2018
  ident: ref28
  article-title: BERT: Pre-training of deep bidirectional transformers for language understanding
  publication-title: arXiv:1810.04805
– start-page: 249
  volume-title: Proc. 13th Int. Conf. Artif. Intell. Statist.
  ident: ref30
  article-title: Understanding the difficulty of training deep feedforward neural networks
– ident: ref21
  doi: 10.1016/j.knosys.2019.06.019
– ident: ref19
  doi: 10.1049/trit.2020.0031
– ident: ref18
  doi: 10.1145/3469213.3470423
– start-page: 1
  volume-title: Proc. Advances Neural Inf. Process. Syst.
  ident: ref27
  article-title: Imagenet classification with deep convolutional neural networks
– ident: ref24
  doi: 10.1109/TMM.2021.3111487
– ident: ref23
  doi: 10.1145/3394171.3413653
– ident: ref14
  doi: 10.1145/1864708.1864770
– start-page: 1
  volume-title: Proc. Adv. Neural Inf. Process. Syst.
  ident: ref31
  article-title: Improved training of Waserstein gans
– ident: ref1
  doi: 10.1145/3209978.3209981
– ident: ref4
  doi: 10.1145/3596250
SSID ssj0024890
Score 2.3891222
Snippet With the rise of e-commerce, personalized recommendation algorithms have received much attention in recent years. Meanwhile, multimodal recommendation...
SourceID crossref
ieee
SourceType Index Database
Publisher
StartPage 15371
SubjectTerms artificial intelligence
Collaborative filtering
Computational modeling
Data mining
Data models
Feature extraction
Motion pictures
Prediction algorithms
predictive models
Recommender system
Recommender systems
Self-supervised learning
Training
Title Multi-Modal Self-Supervised Learning Algorithm-Based Product Recommendation
URI https://ieeexplore.ieee.org/document/10993410
Volume 22
WOSCitedRecordID wos001494111500010&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: 1558-3783
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0024890
  issn: 1545-5955
  databaseCode: RIE
  dateStart: 20040101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3PS8MwFA46POjBnxPnL3rwJGTrmqZJjlMcgjoGm7JbSZOXOdjWsXX-_SZpxV48eCttQsIXkrzvvX7vIXSnMsVjHRtruRmCYwCGM5rFmAuAUEKoYh8x_XhlgwGfTMSwEqt7LQwA-J_PoO0efSxf52rrXGUdF8Wxp65l6LuMJaVY6zexHvcOFWcSYCoorUKYtk9n3Bs9WSoY0TahSambrl1Ctaoq_lLpH_1zOsfosLIeg1653CdoB5an6KCWU_AMvXhJLX7LtW04grnBo-3KHQgb0EGVTXUa9ObTfD0rPhf4QboPwzLxa-DY6MIOW1ZaaqL3_tP48RlXFROwiqKwwLJLjOYJlQQ4GCq4BktAjWaJyEIVcRkry1AgsmYW03azA5M004yCTnRXKEnOUWOZL-ECBYwbu9uB0K4icSiNDLUyQhKmM5FQRlro_gfCdFUmxkg9oQhF6vBOHd5phXcLNR18tYYlcpd_vL9C-6576eq4Ro1ivYUbtKe-itlmfevX_Ru5YqxW
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3JTsMwELVQQQIOrEXs5MAJyW0a27F9LKgIRFtVakG9RY49LpWgRSXl-7GdIHrhwC1KnEXP27yZzBuErnWuBTXUOsvNEkwBOM5ZTrGQALGCWNMQMX3p8n5fjMdyUCWrh1wYAAg_n0HDH4ZYvpnrpXeVNX0Ux626jqGvM0qTuEzX-pXWE8Gl4o0CzCRjVRDT3dUctYcdRwYT1iAsLTOnV7ahlboqYVu53_3nB-2hncp-jNplh--jNZgdoO0VVcFD9BSSanFvblzDIbxZPFx--CXhE0xU6alOovbbZL6YFq_v-Fb5C4NS-jXyfPTdvbastVRHz_ed0d0DrmomYJ0kcYFVi1gjUqYICLBMCgOOglrDU5nHOhGKasdRIHGGFjduugNXLDecgUlNS2pFjlBtNp_BMYq4sG6-A2EtTWisrIqNtlIRbnKZMk5O0M0PhNlHKY2RBUoRy8zjnXm8swrvE1T38K00LJE7_eP8Fdp8GPW6Wfex_3SGtvyjSsfHOaoViyVcoA39VUw_F5dhDHwD4PuvnQ
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=Multi-Modal+Self-Supervised+Learning+Algorithm-Based+Product+Recommendation&rft.jtitle=IEEE+transactions+on+automation+science+and+engineering&rft.au=Gao%2C+Li&rft.au=Fan%2C+Haiping&rft.au=Chen%2C+Qingkui&rft.au=Yang%2C+Heyu&rft.date=2025&rft.issn=1545-5955&rft.eissn=1558-3783&rft.volume=22&rft.spage=15371&rft.epage=15380&rft_id=info:doi/10.1109%2FTASE.2025.3568286&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TASE_2025_3568286
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1545-5955&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1545-5955&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1545-5955&client=summon