Dual-Channel Variational Graph Autoencoder with Hierarchical Contrastive Learning for Recommendation

Dual-Channel Variational Graph Autoencoder with Hierarchical Contrastive Learning for Recommendation | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article Dual-Channel Variational Graph Autoencoder with Hierarchical Contrastive Learning for Recommendation Chenghao Liu, Bohang Yang, Qian Tao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4962855/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract In recent years, Graph Neural Networks (GNNs) have been widely utilized in Recommendation. Although current GNNs-based recommendation algorithms have improved performance, they are still plagued by the data sparsity problem. Contrastive learning, which extracts self-supervised signals from a large amount of unlabeled data through auxiliary tasks, is one of the effective means to alleviate this problem. However, existing contrastive learning based on graph structure augmentation may discard important nodes or edges, resulting in the bias of semantic information; while contrastive learning based on embedding augmentation adds random noise to nodes, ignoring the differences between them. To address this problem, we propose a Dual Channel Variational Graph Autoencoder with Hierarchical Contrastive Learning for Recommendation. First, we use variational graph autoencoder to learn the node representation. Second, the collaborative neighbor graph is constructed through the similarity between users (items), which further models the higher-order signals while preserving the information to achieve global-level contrastive learning. Finally, in each variational graph autoencoder, we sample the embeddings from the Gaussian distribution of the intermediate and the final layer according to its estimator variance, respectively, to realize local-level contrastive learning. Extensive experiments on two real-world datasets show that the model achieves state-of-the-art performance, validating its effectiveness. Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Software Physical sciences/Mathematics and computing/Scientific data Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 05 Nov, 2024 Reviews received at journal 02 Nov, 2024 Reviewers agreed at journal 28 Oct, 2024 Reviews received at journal 10 Sep, 2024 Reviewers agreed at journal 09 Sep, 2024 Reviewers invited by journal 02 Sep, 2024 Editor assigned by journal 02 Sep, 2024 Editor invited by journal 02 Sep, 2024 Submission checks completed at journal 02 Sep, 2024 First submitted to journal 23 Aug, 2024 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4962855","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":359508398,"identity":"0da96f2d-4d19-4622-8570-a7881946009e","order_by":0,"name":"Chenghao Liu","email":"","orcid":"","institution":"South China University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Chenghao","middleName":"","lastName":"Liu","suffix":""},{"id":359508399,"identity":"b1a2e7d0-51d8-4455-95d6-d217cd9e35ae","order_by":1,"name":"Bohang Yang","email":"","orcid":"","institution":"South China University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Bohang","middleName":"","lastName":"Yang","suffix":""},{"id":359508400,"identity":"48d6e57d-9254-45d3-bba0-4cad2a378a7a","order_by":2,"name":"Qian Tao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1ElEQVRIiWNgGAWjYLCCBAYGOSiTmbBqHqgWYyDF2EC8FiBIbCBaiz374YM3HtTcSZ/ffsb8AUOFdWID+9kD+G3hSUu2SDj2LHfDmRzDBoYz6YkNPHkJBByWYyaRwHY4d4MEj2EDY9vhxAYJHgP8WvjfALX8O5wuPwOk5R8xWiSAtiS2HU5guAHS0kCMlhvPki0S+w4bbjiTVjgj4Vi6cRtPDn4t7P3JB2/++HZYXr798IYPH2qsZfvZz+DXAgIScFYCELMRVI+iZRSMglEwCkYBNgAAx0tDuGFChS8AAAAASUVORK5CYII=","orcid":"","institution":"South China University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Qian","middleName":"","lastName":"Tao","suffix":""}],"badges":[],"createdAt":"2024-08-23 08:53:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4962855/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4962855/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":65855806,"identity":"12ff8359-0405-4e3d-a9e9-da216a001d41","added_by":"auto","created_at":"2024-10-03 15:10:47","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":689603,"visible":true,"origin":"","legend":"","description":"","filename":"ScientificReports.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4962855/v1_covered_26b48724-efb6-4286-95be-5eac7b17582a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Dual-Channel Variational Graph Autoencoder with Hierarchical Contrastive Learning for Recommendation","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-4962855/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4962855/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In recent years, Graph Neural Networks (GNNs) have been widely utilized in Recommendation. Although current GNNs-based recommendation algorithms have improved performance, they are still plagued by the data sparsity problem. Contrastive learning, which extracts self-supervised signals from a large amount of unlabeled data through auxiliary tasks, is one of the effective means to alleviate this problem. However, existing contrastive learning based on graph structure augmentation may discard important nodes or edges, resulting in the bias of semantic information; while contrastive learning based on embedding augmentation adds random noise to nodes, ignoring the differences between them. To address this problem, we propose a Dual Channel Variational Graph Autoencoder with Hierarchical Contrastive Learning for Recommendation. First, we use variational graph autoencoder to learn the node representation. Second, the collaborative neighbor graph is constructed through the similarity between users (items), which further models the higher-order signals while preserving the information to achieve global-level contrastive learning. Finally, in each variational graph autoencoder, we sample the embeddings from the Gaussian distribution of the intermediate and the final layer according to its estimator variance, respectively, to realize local-level contrastive learning. Extensive experiments on two real-world datasets show that the model achieves state-of-the-art performance, validating its effectiveness.","manuscriptTitle":"Dual-Channel Variational Graph Autoencoder with Hierarchical Contrastive Learning for Recommendation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-10-03 15:02:39","doi":"10.21203/rs.3.rs-4962855/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-11-05T15:44:47+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-11-02T22:50:45+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"141010122961336320701994384347776018906","date":"2024-10-28T12:46:51+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-09-10T14:53:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"132636568860825114936362587314962285683","date":"2024-09-09T15:25:13+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-09-02T14:37:37+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-09-02T14:30:25+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-09-02T06:53:47+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-09-02T06:40:32+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-08-23T08:49:44+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"4f9827ec-0775-4f90-b279-43a65cfafa52","owner":[],"postedDate":"October 3rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":38257236,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":38257237,"name":"Physical sciences/Mathematics and computing/Software"},{"id":38257238,"name":"Physical sciences/Mathematics and computing/Scientific data"}],"tags":[],"updatedAt":"2024-12-10T16:38:25+00:00","versionOfRecord":[],"versionCreatedAt":"2024-10-03 15:02:39","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4962855","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4962855","identity":"rs-4962855","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}