Reconstructed Graph Constrained Auto-Encoders for Multi-View Representation Learning

The application of Auto-Encoder (AE) to multi-view representation learning has gained traction due to advancements in deep learning. While some current AE-based multi-view representation learning algorithms incorporate the geometric structure of the input data into their feature representation learn...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on multimedia 2024, Vol.26, p.1319-1332
Hauptverfasser: Gou, Jianping, Xie, Nannan, Yuan, Yunhao, Du, Lan, Ou, Weihua, Yi, Zhang
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 1332
container_issue
container_start_page 1319
container_title IEEE transactions on multimedia
container_volume 26
creator Gou, Jianping
Xie, Nannan
Yuan, Yunhao
Du, Lan
Ou, Weihua
Yi, Zhang
description The application of Auto-Encoder (AE) to multi-view representation learning has gained traction due to advancements in deep learning. While some current AE-based multi-view representation learning algorithms incorporate the geometric structure of the input data into their feature representation learning process, their use of a shallow structured graph regularization term can be restrictive when used in conjunction with deep models. Furthermore, current multi-view representation learning algorithms do not fully utilize the diversity and consistency presented in different views, leading to a reduction in the efficacy of feature learning. This paper introduces a novel approach, reconstructed graph constrained auto-encoders (RGCAE), for multi-view representation learning. Unlike existing methods, our approach incorporates deep adaptive graph regularization based on multi-layer perceptron to ensure the preservation of the geometric similarity graph, which is constructed based on the local invariance principle. By decoupling the feature representation learning from the preservation of the geometric structure among different views, our approach can better leverage the diversity presented in multi-view data. We obtain view-specific representations that preserve the geometric structure and then combine them by averaging to obtain a common representation. To ensure the consistency of the multi-view data, we minimize the loss between the view-specific and common representations. Consequently, our RGCAE approach can maintain the geometric structure of multi-view data and is better suited for integration with deep models. Extensive experiments on six datasets demonstrate that RGCAE obtained promising performance, compared with the state-of-the-art methods.
doi_str_mv 10.1109/TMM.2023.3279988
format Article
fullrecord <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_TMM_2023_3279988</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10134758</ieee_id><sourcerecordid>2916481838</sourcerecordid><originalsourceid>FETCH-LOGICAL-c292t-54c3713ad47cd184f9604802241702b7d9d6966246fdb7149d477d62224e07b43</originalsourceid><addsrcrecordid>eNpNkE1LAzEQhoMoWKt3Dx4WPG-dfGw-jqXUKrQIpXoN201Wt9RkTbKI_97U9uBphpfnnYEHoVsME4xBPWxWqwkBQieUCKWkPEMjrBguAYQ4z3tFoFQEwyW6inEHgFkFYoQ2a9t4F1MYmmRNsQh1_1HM_pK6czmZDsmXc9d4Y0MsWh-K1bBPXfnW2e9ibftgo3WpTp13xdLWwXXu_RpdtPU-2pvTHKPXx_lm9lQuXxbPs-mybIgiqaxYQwWmtWGiMViyVnFgEghhWADZCqMMV5wTxluzFZipDArDSQYsiC2jY3R_vNsH_zXYmPTOD8Hll5oozJnEkspMwZFqgo8x2Fb3ofusw4_GoA_udHanD-70yV2u3B0rnbX2H44pE5Wkv1OaaaA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2916481838</pqid></control><display><type>article</type><title>Reconstructed Graph Constrained Auto-Encoders for Multi-View Representation Learning</title><source>IEEE Electronic Library (IEL)</source><creator>Gou, Jianping ; Xie, Nannan ; Yuan, Yunhao ; Du, Lan ; Ou, Weihua ; Yi, Zhang</creator><creatorcontrib>Gou, Jianping ; Xie, Nannan ; Yuan, Yunhao ; Du, Lan ; Ou, Weihua ; Yi, Zhang</creatorcontrib><description>The application of Auto-Encoder (AE) to multi-view representation learning has gained traction due to advancements in deep learning. While some current AE-based multi-view representation learning algorithms incorporate the geometric structure of the input data into their feature representation learning process, their use of a shallow structured graph regularization term can be restrictive when used in conjunction with deep models. Furthermore, current multi-view representation learning algorithms do not fully utilize the diversity and consistency presented in different views, leading to a reduction in the efficacy of feature learning. This paper introduces a novel approach, reconstructed graph constrained auto-encoders (RGCAE), for multi-view representation learning. Unlike existing methods, our approach incorporates deep adaptive graph regularization based on multi-layer perceptron to ensure the preservation of the geometric similarity graph, which is constructed based on the local invariance principle. By decoupling the feature representation learning from the preservation of the geometric structure among different views, our approach can better leverage the diversity presented in multi-view data. We obtain view-specific representations that preserve the geometric structure and then combine them by averaging to obtain a common representation. To ensure the consistency of the multi-view data, we minimize the loss between the view-specific and common representations. Consequently, our RGCAE approach can maintain the geometric structure of multi-view data and is better suited for integration with deep models. Extensive experiments on six datasets demonstrate that RGCAE obtained promising performance, compared with the state-of-the-art methods.</description><identifier>ISSN: 1520-9210</identifier><identifier>EISSN: 1941-0077</identifier><identifier>DOI: 10.1109/TMM.2023.3279988</identifier><identifier>CODEN: ITMUF8</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Algorithms ; Auto-encoders ; Coders ; Consistency ; Data models ; Decoupling ; Deep learning ; Laplace equations ; Linear programming ; Machine learning ; Manifold learning ; Multi-view representation learning ; Multilayer perceptrons ; Multilayers ; Neural networks ; Reconstructed graph regularization ; Regularization ; Representation learning ; Representations</subject><ispartof>IEEE transactions on multimedia, 2024, Vol.26, p.1319-1332</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c292t-54c3713ad47cd184f9604802241702b7d9d6966246fdb7149d477d62224e07b43</citedby><cites>FETCH-LOGICAL-c292t-54c3713ad47cd184f9604802241702b7d9d6966246fdb7149d477d62224e07b43</cites><orcidid>0000-0002-5867-9322 ; 0000-0003-3712-443X ; 0000-0001-5241-7703 ; 0000-0002-9925-0223 ; 0000-0003-1413-0693</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10134758$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,4024,27923,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/10134758$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Gou, Jianping</creatorcontrib><creatorcontrib>Xie, Nannan</creatorcontrib><creatorcontrib>Yuan, Yunhao</creatorcontrib><creatorcontrib>Du, Lan</creatorcontrib><creatorcontrib>Ou, Weihua</creatorcontrib><creatorcontrib>Yi, Zhang</creatorcontrib><title>Reconstructed Graph Constrained Auto-Encoders for Multi-View Representation Learning</title><title>IEEE transactions on multimedia</title><addtitle>TMM</addtitle><description>The application of Auto-Encoder (AE) to multi-view representation learning has gained traction due to advancements in deep learning. While some current AE-based multi-view representation learning algorithms incorporate the geometric structure of the input data into their feature representation learning process, their use of a shallow structured graph regularization term can be restrictive when used in conjunction with deep models. Furthermore, current multi-view representation learning algorithms do not fully utilize the diversity and consistency presented in different views, leading to a reduction in the efficacy of feature learning. This paper introduces a novel approach, reconstructed graph constrained auto-encoders (RGCAE), for multi-view representation learning. Unlike existing methods, our approach incorporates deep adaptive graph regularization based on multi-layer perceptron to ensure the preservation of the geometric similarity graph, which is constructed based on the local invariance principle. By decoupling the feature representation learning from the preservation of the geometric structure among different views, our approach can better leverage the diversity presented in multi-view data. We obtain view-specific representations that preserve the geometric structure and then combine them by averaging to obtain a common representation. To ensure the consistency of the multi-view data, we minimize the loss between the view-specific and common representations. Consequently, our RGCAE approach can maintain the geometric structure of multi-view data and is better suited for integration with deep models. Extensive experiments on six datasets demonstrate that RGCAE obtained promising performance, compared with the state-of-the-art methods.</description><subject>Algorithms</subject><subject>Auto-encoders</subject><subject>Coders</subject><subject>Consistency</subject><subject>Data models</subject><subject>Decoupling</subject><subject>Deep learning</subject><subject>Laplace equations</subject><subject>Linear programming</subject><subject>Machine learning</subject><subject>Manifold learning</subject><subject>Multi-view representation learning</subject><subject>Multilayer perceptrons</subject><subject>Multilayers</subject><subject>Neural networks</subject><subject>Reconstructed graph regularization</subject><subject>Regularization</subject><subject>Representation learning</subject><subject>Representations</subject><issn>1520-9210</issn><issn>1941-0077</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkE1LAzEQhoMoWKt3Dx4WPG-dfGw-jqXUKrQIpXoN201Wt9RkTbKI_97U9uBphpfnnYEHoVsME4xBPWxWqwkBQieUCKWkPEMjrBguAYQ4z3tFoFQEwyW6inEHgFkFYoQ2a9t4F1MYmmRNsQh1_1HM_pK6czmZDsmXc9d4Y0MsWh-K1bBPXfnW2e9ibftgo3WpTp13xdLWwXXu_RpdtPU-2pvTHKPXx_lm9lQuXxbPs-mybIgiqaxYQwWmtWGiMViyVnFgEghhWADZCqMMV5wTxluzFZipDArDSQYsiC2jY3R_vNsH_zXYmPTOD8Hll5oozJnEkspMwZFqgo8x2Fb3ofusw4_GoA_udHanD-70yV2u3B0rnbX2H44pE5Wkv1OaaaA</recordid><startdate>2024</startdate><enddate>2024</enddate><creator>Gou, Jianping</creator><creator>Xie, Nannan</creator><creator>Yuan, Yunhao</creator><creator>Du, Lan</creator><creator>Ou, Weihua</creator><creator>Yi, Zhang</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0002-5867-9322</orcidid><orcidid>https://orcid.org/0000-0003-3712-443X</orcidid><orcidid>https://orcid.org/0000-0001-5241-7703</orcidid><orcidid>https://orcid.org/0000-0002-9925-0223</orcidid><orcidid>https://orcid.org/0000-0003-1413-0693</orcidid></search><sort><creationdate>2024</creationdate><title>Reconstructed Graph Constrained Auto-Encoders for Multi-View Representation Learning</title><author>Gou, Jianping ; Xie, Nannan ; Yuan, Yunhao ; Du, Lan ; Ou, Weihua ; Yi, Zhang</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c292t-54c3713ad47cd184f9604802241702b7d9d6966246fdb7149d477d62224e07b43</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Algorithms</topic><topic>Auto-encoders</topic><topic>Coders</topic><topic>Consistency</topic><topic>Data models</topic><topic>Decoupling</topic><topic>Deep learning</topic><topic>Laplace equations</topic><topic>Linear programming</topic><topic>Machine learning</topic><topic>Manifold learning</topic><topic>Multi-view representation learning</topic><topic>Multilayer perceptrons</topic><topic>Multilayers</topic><topic>Neural networks</topic><topic>Reconstructed graph regularization</topic><topic>Regularization</topic><topic>Representation learning</topic><topic>Representations</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Gou, Jianping</creatorcontrib><creatorcontrib>Xie, Nannan</creatorcontrib><creatorcontrib>Yuan, Yunhao</creatorcontrib><creatorcontrib>Du, Lan</creatorcontrib><creatorcontrib>Ou, Weihua</creatorcontrib><creatorcontrib>Yi, Zhang</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE transactions on multimedia</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Gou, Jianping</au><au>Xie, Nannan</au><au>Yuan, Yunhao</au><au>Du, Lan</au><au>Ou, Weihua</au><au>Yi, Zhang</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Reconstructed Graph Constrained Auto-Encoders for Multi-View Representation Learning</atitle><jtitle>IEEE transactions on multimedia</jtitle><stitle>TMM</stitle><date>2024</date><risdate>2024</risdate><volume>26</volume><spage>1319</spage><epage>1332</epage><pages>1319-1332</pages><issn>1520-9210</issn><eissn>1941-0077</eissn><coden>ITMUF8</coden><abstract>The application of Auto-Encoder (AE) to multi-view representation learning has gained traction due to advancements in deep learning. While some current AE-based multi-view representation learning algorithms incorporate the geometric structure of the input data into their feature representation learning process, their use of a shallow structured graph regularization term can be restrictive when used in conjunction with deep models. Furthermore, current multi-view representation learning algorithms do not fully utilize the diversity and consistency presented in different views, leading to a reduction in the efficacy of feature learning. This paper introduces a novel approach, reconstructed graph constrained auto-encoders (RGCAE), for multi-view representation learning. Unlike existing methods, our approach incorporates deep adaptive graph regularization based on multi-layer perceptron to ensure the preservation of the geometric similarity graph, which is constructed based on the local invariance principle. By decoupling the feature representation learning from the preservation of the geometric structure among different views, our approach can better leverage the diversity presented in multi-view data. We obtain view-specific representations that preserve the geometric structure and then combine them by averaging to obtain a common representation. To ensure the consistency of the multi-view data, we minimize the loss between the view-specific and common representations. Consequently, our RGCAE approach can maintain the geometric structure of multi-view data and is better suited for integration with deep models. Extensive experiments on six datasets demonstrate that RGCAE obtained promising performance, compared with the state-of-the-art methods.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/TMM.2023.3279988</doi><tpages>14</tpages><orcidid>https://orcid.org/0000-0002-5867-9322</orcidid><orcidid>https://orcid.org/0000-0003-3712-443X</orcidid><orcidid>https://orcid.org/0000-0001-5241-7703</orcidid><orcidid>https://orcid.org/0000-0002-9925-0223</orcidid><orcidid>https://orcid.org/0000-0003-1413-0693</orcidid></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1520-9210
ispartof IEEE transactions on multimedia, 2024, Vol.26, p.1319-1332
issn 1520-9210
1941-0077
language eng
recordid cdi_crossref_primary_10_1109_TMM_2023_3279988
source IEEE Electronic Library (IEL)
subjects Algorithms
Auto-encoders
Coders
Consistency
Data models
Decoupling
Deep learning
Laplace equations
Linear programming
Machine learning
Manifold learning
Multi-view representation learning
Multilayer perceptrons
Multilayers
Neural networks
Reconstructed graph regularization
Regularization
Representation learning
Representations
title Reconstructed Graph Constrained Auto-Encoders for Multi-View Representation Learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T16%3A11%3A10IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Reconstructed%20Graph%20Constrained%20Auto-Encoders%20for%20Multi-View%20Representation%20Learning&rft.jtitle=IEEE%20transactions%20on%20multimedia&rft.au=Gou,%20Jianping&rft.date=2024&rft.volume=26&rft.spage=1319&rft.epage=1332&rft.pages=1319-1332&rft.issn=1520-9210&rft.eissn=1941-0077&rft.coden=ITMUF8&rft_id=info:doi/10.1109/TMM.2023.3279988&rft_dat=%3Cproquest_RIE%3E2916481838%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2916481838&rft_id=info:pmid/&rft_ieee_id=10134758&rfr_iscdi=true