Incomplete Multi-View Multi-Label Learning via Disentangled Representation and Label Semantic Embedding

In incomplete multi-view multi-label learning scenarios, it is crucial to use the incomplete multi-view data to extract consistent and specific representations from different data sources and to fully exploit the missing label information. However, most previous approaches ignore the separation prob...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) S. 30722 - 30731
Hauptverfasser: Yan, Xu, Yin, Jun, Wen, Jie
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 10.06.2025
Schlagworte:
ISSN:1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract In incomplete multi-view multi-label learning scenarios, it is crucial to use the incomplete multi-view data to extract consistent and specific representations from different data sources and to fully exploit the missing label information. However, most previous approaches ignore the separation problem between view-shared and specific information. To address this problem, in this paper, we propose a method that can separate view-consistent features from view-specific features under the Variational Autoen-coder (VAE) framework. Specifically, we first introduce cross-view reconstruction to capture view-consistent features and extract shared information from different views through unsupervised pre-training. Subsequently, we develop a disentangling module to learn specific features by minimizing the variational upper bound of mutual information between consistent and specific features. Finally, we utilize prior label relevance information derived from training data to guide the learning of the distribution of label semantic embeddings, aggregating relevant semantic embeddings and maintaining the label relevance topology in the semantic space. In extensive experiments, our model outperforms existing state-of-the-art algorithms on several real-world datasets, which fully validates its strong adaptability to missing views and labels.
AbstractList In incomplete multi-view multi-label learning scenarios, it is crucial to use the incomplete multi-view data to extract consistent and specific representations from different data sources and to fully exploit the missing label information. However, most previous approaches ignore the separation problem between view-shared and specific information. To address this problem, in this paper, we propose a method that can separate view-consistent features from view-specific features under the Variational Autoen-coder (VAE) framework. Specifically, we first introduce cross-view reconstruction to capture view-consistent features and extract shared information from different views through unsupervised pre-training. Subsequently, we develop a disentangling module to learn specific features by minimizing the variational upper bound of mutual information between consistent and specific features. Finally, we utilize prior label relevance information derived from training data to guide the learning of the distribution of label semantic embeddings, aggregating relevant semantic embeddings and maintaining the label relevance topology in the semantic space. In extensive experiments, our model outperforms existing state-of-the-art algorithms on several real-world datasets, which fully validates its strong adaptability to missing views and labels.
Author Yan, Xu
Yin, Jun
Wen, Jie
Author_xml – sequence: 1
  givenname: Xu
  surname: Yan
  fullname: Yan, Xu
  email: yanxu@stu.shmtu.edu.cn
  organization: Shanghai Maritime University
– sequence: 2
  givenname: Jun
  surname: Yin
  fullname: Yin, Jun
  email: junyin@shmtu.edu.cn
  organization: Shanghai Maritime University
– sequence: 3
  givenname: Jie
  surname: Wen
  fullname: Wen, Jie
  email: jiewen_pr@126.com
  organization: Harbin Institute of Technology,Shenzhen
BookMark eNotkMtOwzAURA0CiVL6B134B1J87Ti2l6gUqBQEKlW31XV8UxklbpUEEH_Po13NmcWZxVyzi7RPxNgUxAxAuNv55nWlpVH5TAqpZ0LaAs7YxBlnlQKdqyK352wEolBZ4cBdsUnfvwshlAQonB2x3TJV-_bQ0ED8-aMZYraJ9HXCEj01vCTsUkw7_hmR38ee0oBp11DgKzp09N-HuE8cU-BH5Y1aTEOs-KL1FMKvfMMua2x6mpxyzNYPi_X8KStfHpfzuzKLTg2Z9UFrJPSo6ko7tAFlqCF3PkivjfHG1jmAIQ9VUZiKMBfeoRIOPBlCNWbT42wkou2hiy1239u_r6SVVv0AM1BcCQ
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/CVPR52734.2025.02861
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Applied Sciences
EISBN 9798331543648
EISSN 1063-6919
EndPage 30731
ExternalDocumentID 11092828
Genre orig-research
GrantInformation_xml – fundername: National Natural Science Foundation of China
  funderid: 10.13039/501100001809
GroupedDBID 6IE
6IH
6IL
6IN
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-i93t-8bd55aeaba3fc59a8da2df149bd2b577b78f4117eb1c667cea40b9a3091be7ea3
IEDL.DBID RIE
IngestDate Wed Aug 20 06:20:57 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i93t-8bd55aeaba3fc59a8da2df149bd2b577b78f4117eb1c667cea40b9a3091be7ea3
PageCount 10
ParticipantIDs ieee_primary_11092828
PublicationCentury 2000
PublicationDate 2025-June-10
PublicationDateYYYYMMDD 2025-06-10
PublicationDate_xml – month: 06
  year: 2025
  text: 2025-June-10
  day: 10
PublicationDecade 2020
PublicationTitle Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online)
PublicationTitleAbbrev CVPR
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003211698
Score 2.294198
Snippet In incomplete multi-view multi-label learning scenarios, it is crucial to use the incomplete multi-view data to extract consistent and specific representations...
SourceID ieee
SourceType Publisher
StartPage 30722
SubjectTerms Computer vision
Data mining
Disentangled representation learning
Feature extraction
Mutual information
Semantics
Soft sensors
Topology
Training data
Upper bound
Title Incomplete Multi-View Multi-Label Learning via Disentangled Representation and Label Semantic Embedding
URI https://ieeexplore.ieee.org/document/11092828
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JbwIhFCbV9NCTXWy6h0Ov6IzAwJytTQ_GGGuMN_MY3phJdGzc-vcLONVTD70RwpZH4C2874OQV-dlaInKMIgjzgR0YmZSIVjE89QIbkEF2sVJXw0GejpNhxVYPWBhEDEkn2HLF8Nbvl1lOx8qa3t2TO8i1EhNqeQA1joGVLhzZZJUV_A417LdnQxHnl_Mh046suU0aaDCPn2iEnTIe-Ofs1-S5gmNR4dHPXNFzrC8Jo3KfKTV4dzckLk76z5B3JnBNOBq2aTA76rYB4MLWrGpzum-APpWBOBROV-4YUYhI7YCIpUUSksPXT5x6YRfZLS3NGj9Cppk_N4bdz9Y9Y8CK1K-ZdpYKQHBAM8zmYK20LG584yM7RiplFE6F3Gs3K2dJYnKEERkUuDOkjCoEPgtqZerEu8INQCYJdKZlIjCugtKG52ISDgJ6JhLfU-aXm6zrwNTxuxXZA9_1D-SC781PvUqjp5Ifbve4TM5z_bbYrN-Cfv7AwUtqFI
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JTwIxFG4UTfSEC8bdHrwOzEzbaeeMGIwjIUgIN9JOH2QSGAybf9-2VDh58NY03fKa9i1931eEno2XIRhwFcgoJAGVcRSolNIgJONUUaIld7SLg4x3OmI4TLserO6wMADgks-gbovuLV_P87UNlTUsO6Z1EQ7REaM0DrdwrV1IhRhnJkmFB8iZto3moNuzDGM2eBKzutGljgx7_42K0yKv1X_Of4Zqezwe7u40zTk6gPICVb0Bif3xXF6iiTntNkXcGMLYIWuDQQHfvphJBVPs-VQneFNI_FI46FE5mZphei4n1kORSixLjbddPmFmxF_kuDVToO0Kaqj_2uo324H_SSEoUrIKhNKMSZBKknHOUim0jPXY-EZKx4pxrrgY0yji5t7Ok4TnIGmoUkmMLaGAgyRXqFLOS7hGWEkJecKMUQlAtbmihBIJDamRgIgIEzeoZuU2-tpyZYx-RXb7R_0TOmn3P7JR9tZ5v0OndptsIlYU3qPKarGGB3Scb1bFcvHo9voH8R2rmQ
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%3Abook&rft.genre=proceeding&rft.title=Proceedings+%28IEEE+Computer+Society+Conference+on+Computer+Vision+and+Pattern+Recognition.+Online%29&rft.atitle=Incomplete+Multi-View+Multi-Label+Learning+via+Disentangled+Representation+and+Label+Semantic+Embedding&rft.au=Yan%2C+Xu&rft.au=Yin%2C+Jun&rft.au=Wen%2C+Jie&rft.date=2025-06-10&rft.pub=IEEE&rft.eissn=1063-6919&rft.spage=30722&rft.epage=30731&rft_id=info:doi/10.1109%2FCVPR52734.2025.02861&rft.externalDocID=11092828