VR-GNN: Variational Relation Vector Graph Neural Network for Modeling Homophily and Heterophily

VR-GNN: Variational Relation Vector Graph Neural Network for Modeling Homophily and Heterophily | 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 Research Article VR-GNN: Variational Relation Vector Graph Neural Network for Modeling Homophily and Heterophily Fengzhao Shi, Ren Li, Yanan Cao, Xixun Lin, Yanmin Shang, Chuan Zhou, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3842969/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 01 May, 2024 Read the published version in World Wide Web → Version 1 posted 7 You are reading this latest preprint version Abstract Graph Neural Networks (GNNs) have achieved remarkable success in diverse real-world applications. Traditional GNNs are designed based on homophily, which leads to poor performance under heterophily scenarios. Most current solutions deal with heterophily mainly by modeling the heterophily edges as data noises or high-frequency signals, treating all heterophilic edges as being of the same semantic. Consequently, they ignore the rich semantic information of these edges in heterophily graphs. To overcome this critic problem, we propose a novel GNN model based on relation vector translation named as Variational Relation Vector Graph Neural Network (VR-GNN). VR-GNN models relation generation and graph aggregation into an end-to-end model based on a variational inference framework. To be specific, the encoder utilizes the structure, feature and label to generate a fine-grained relation vector for each edge, which aims to infer its implicit semantic information. The decoder incorporates the generated relation vectors into the message-passing framework for deriving better node representations. We conduct extensive experiments on eight real-world datasets with different homophily-heterophily properties to verify model effectiveness. Extensive experimental results show that VR-GNN gains consistent and significant improvements against existing strong GNN methods under heterophily and competitive performance under homophily. Data mining Graph neural networks Semi-supervised node classification Social network Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 01 May, 2024 Read the published version in World Wide Web → Version 1 posted Editorial decision: Revision requested 27 Jan, 2024 Reviews received at journal 16 Jan, 2024 Reviewers agreed at journal 14 Jan, 2024 Reviewers invited by journal 14 Jan, 2024 Editor assigned by journal 09 Jan, 2024 Submission checks completed at journal 09 Jan, 2024 First submitted to journal 07 Jan, 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-3842969","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":266201728,"identity":"74f2d635-3230-40c5-a164-564e16bd91a5","order_by":0,"name":"Fengzhao Shi","email":"","orcid":"","institution":"School of Cyber Security, University of Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Fengzhao","middleName":"","lastName":"Shi","suffix":""},{"id":266201729,"identity":"3d963970-dade-4103-a2ef-70cbb8dd13d7","order_by":1,"name":"Ren Li","email":"","orcid":"","institution":"School of Cyber Security, University of Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Ren","middleName":"","lastName":"Li","suffix":""},{"id":266201730,"identity":"8ee78111-4e30-45f9-a0a4-5e005a531e52","order_by":2,"name":"Yanan Cao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAz0lEQVRIiWNgGAWjYDADfmbGBhK1SDaTrMXgALEq+dsPH5P4ucMuz/g4c+MDhho7Bv7ZBGyTOJOWJtl7JrnY7DBjswHDsWQGiTsE7DNgyDGT4G1jTtx2mLFNgoHtAIOBRAIBLfxvzCT/ttUnbm5mbP/B8I8YLRI5ZtK8bYcTNzAztjEwthGhReLGs2Rr2bbjiTOAfpFI7EvmkbhBQAt/f/LBm2/bqhP7+48//PDhm50c/wwCWoCARQLOBCrmIageCJg/EKNqFIyCUTAKRjAAAHfuPobReEXpAAAAAElFTkSuQmCC","orcid":"","institution":"School of Cyber Security, University of Chinese Academy of Sciences","correspondingAuthor":true,"prefix":"","firstName":"Yanan","middleName":"","lastName":"Cao","suffix":""},{"id":266201731,"identity":"f6fac87d-a6bb-461d-92e9-7c22525cc99b","order_by":3,"name":"Xixun Lin","email":"","orcid":"","institution":"School of Cyber Security, University of Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Xixun","middleName":"","lastName":"Lin","suffix":""},{"id":266201732,"identity":"28c2398b-19d1-472c-8e02-3150320e39a9","order_by":4,"name":"Yanmin Shang","email":"","orcid":"","institution":"School of Cyber Security, University of Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Yanmin","middleName":"","lastName":"Shang","suffix":""},{"id":266201733,"identity":"6005e3e4-60ef-4735-b59c-7bd568085556","order_by":5,"name":"Chuan Zhou","email":"","orcid":"","institution":"Chinese Academy of Sciences","correspondingAuthor":false,"prefix":"","firstName":"Chuan","middleName":"","lastName":"Zhou","suffix":""},{"id":266201734,"identity":"a747c290-1d75-4258-ab17-89a756b125c4","order_by":6,"name":"Jia Wu","email":"","orcid":"","institution":"Macquarie University","correspondingAuthor":false,"prefix":"","firstName":"Jia","middleName":"","lastName":"Wu","suffix":""},{"id":266201735,"identity":"0ea85d6c-d5c6-4b4d-adb9-8def091834b5","order_by":7,"name":"Shirui Pan","email":"","orcid":"","institution":"Griffith University","correspondingAuthor":false,"prefix":"","firstName":"Shirui","middleName":"","lastName":"Pan","suffix":""}],"badges":[],"createdAt":"2024-01-07 16:14:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3842969/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3842969/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11280-024-01261-8","type":"published","date":"2024-05-01T04:00:18+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":56140411,"identity":"bd7839ac-70e0-47f6-890f-5bca700cb25f","added_by":"auto","created_at":"2024-05-09 04:23:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1784135,"visible":true,"origin":"","legend":"","description":"","filename":"WWWJVRGNN.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3842969/v1_covered_a317d61e-4d4f-4efd-b7d5-203c42dc10ef.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"VR-GNN: Variational Relation Vector Graph Neural Network for Modeling Homophily and Heterophily","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":"world-wide-web","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"wwwj","sideBox":"Learn more about [World Wide Web](http://link.springer.com/journal/11280)","snPcode":"11280","submissionUrl":"https://submission.nature.com/new-submission/11280/3","title":"World Wide Web","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Data mining, Graph neural networks, Semi-supervised node classification, Social network","lastPublishedDoi":"10.21203/rs.3.rs-3842969/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3842969/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Graph Neural Networks (GNNs) have achieved remarkable success in diverse real-world applications. Traditional GNNs are designed based on homophily, which leads to poor performance under heterophily scenarios. Most current solutions deal with heterophily mainly by modeling the heterophily edges as data noises or high-frequency signals, treating all heterophilic edges as being of the same semantic. Consequently, they ignore the rich semantic information of these edges in heterophily graphs. To overcome this critic problem, we propose a novel GNN model based on relation vector translation named as Variational Relation Vector Graph Neural Network (VR-GNN). VR-GNN models relation generation and graph aggregation into an end-to-end model based on a variational inference framework. To be specific, the encoder utilizes the structure, feature and label to generate a fine-grained relation vector for each edge, which aims to infer its implicit semantic information. The decoder incorporates the generated relation vectors into the message-passing framework for deriving better node representations. We conduct extensive experiments on eight real-world datasets with different homophily-heterophily properties to verify model effectiveness. Extensive experimental results show that VR-GNN gains consistent and significant improvements against existing strong GNN methods under heterophily and competitive performance under homophily.","manuscriptTitle":"VR-GNN: Variational Relation Vector Graph Neural Network for Modeling Homophily and Heterophily","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-11 06:21:31","doi":"10.21203/rs.3.rs-3842969/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-01-27T07:36:43+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-01-16T08:12:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"706ba065-3f74-4356-93f3-ef19093ed0bc","date":"2024-01-15T03:38:32+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-01-15T03:33:40+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-01-10T03:14:34+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-01-09T12:13:07+00:00","index":"","fulltext":""},{"type":"submitted","content":"World Wide Web","date":"2024-01-07T16:07:06+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"world-wide-web","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"wwwj","sideBox":"Learn more about [World Wide Web](http://link.springer.com/journal/11280)","snPcode":"11280","submissionUrl":"https://submission.nature.com/new-submission/11280/3","title":"World Wide Web","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"dcd324db-b9a9-4e62-94bd-8573f122d8c3","owner":[],"postedDate":"January 11th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-05-09T04:00:19+00:00","versionOfRecord":{"articleIdentity":"rs-3842969","link":"https://doi.org/10.1007/s11280-024-01261-8","journal":{"identity":"world-wide-web","isVorOnly":false,"title":"World Wide Web"},"publishedOn":"2024-05-01 04:00:18","publishedOnDateReadable":"May 1st, 2024"},"versionCreatedAt":"2024-01-11 06:21:31","video":"","vorDoi":"10.1007/s11280-024-01261-8","vorDoiUrl":"https://doi.org/10.1007/s11280-024-01261-8","workflowStages":[]},"version":"v1","identity":"rs-3842969","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3842969","identity":"rs-3842969","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}