Self-Supervised Heterogeneous Graph Neural Network with Multi-Scale Meta-Path Contrastive Learning

Self-Supervised Heterogeneous Graph Neural Network with Multi-Scale Meta-Path Contrastive Learning | 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 Self-Supervised Heterogeneous Graph Neural Network with Multi-Scale Meta-Path Contrastive Learning Wu Yufei, Mu yingxue, Wen Xiumei, Meng Fanxing This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6201452/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract Heterogeneous graph neural networks (HGNNs) exhibit remarkable capabilities in modeling complex structures and multi-semantic information. However, existing methods mainly focus on capturing high-order association patterns between heterogeneous nodes when constructing meta-paths, while they often lack sufficient expressive power for local neighborhood information. This limitation hinders their ability to effectively model both global and local structural relationships. To address this issue, we propose a self-supervised heterogeneous graph neural network (HMMC) based on multi-scale meta-path contrastive learning. The proposed approach introduces a multi-scale meta-path embedding mechanism that jointly captures both local and global structural information. Additionally, we design a cross-view self-supervised contrastive learning framework to optimize representations across multiple views, thereby enhancing the model's capacity to represent heterogeneous graph topological structures. To effectively mitigate the negative sample noise that often interferes with model optimization in traditional contrastive learning methods, we propose a novel star-shaped contrastive loss. This loss function ensures the representational consistency of positive sample pairs by constructing a multi-level optimization strategy involving center nodes, positive samples, and negative samples. Experimental results show that the proposed method outperforms existing state-of-the-art approaches across multiple datasets, achieving performance improvements of 0.5–4.1%, thus fully validating its representational capacity, robustness, and generalizability in heterogeneous graph learning tasks. Heterogeneous Neural Networks Self-Supervised Learning Meta-Path Star-Shaped Contrastive Loss Function Contrastive Learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 27 May, 2025 Reviews received at journal 14 May, 2025 Reviews received at journal 04 May, 2025 Reviews received at journal 04 May, 2025 Reviewers agreed at journal 27 Apr, 2025 Reviewers agreed at journal 26 Apr, 2025 Reviewers agreed at journal 25 Apr, 2025 Reviewers invited by journal 25 Apr, 2025 Editor assigned by journal 15 Mar, 2025 Submission checks completed at journal 14 Mar, 2025 First submitted to journal 11 Mar, 2025 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-6201452","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":448590280,"identity":"34e08ecf-4f45-405d-bb00-1ddd1900ae77","order_by":0,"name":"Wu Yufei","email":"","orcid":"","institution":"Hebei University of Architecture","correspondingAuthor":false,"prefix":"","firstName":"Wu","middleName":"","lastName":"Yufei","suffix":""},{"id":448590281,"identity":"0604e2f6-15dc-41f6-b786-33b8748950e7","order_by":1,"name":"Mu yingxue","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwklEQVRIiWNgGAWjYJCCA2CSvbHxwQfStPAcbjacQZpdEult0hzEKNSdkWN4uODX4cR+yYcN0gwMdnK6DQS0mN3IMTg8sy8tcebsxAbjAoZkY7MDxGjh7bFJ3HA7sSF5BsOBxG1EapFI3H/zYMNhHqK18PwA2iLB2NhMnJYzzwoO8zakGc84k9jMOMOAGL8cT978mefPYdn+9uPPf3yosJMjqIWBgcOAgbENxjEgqBwE2B8wMPwhSuUoGAWjYBSMVAAAyLlLDSgTT9MAAAAASUVORK5CYII=","orcid":"","institution":"Hebei University of Architecture","correspondingAuthor":true,"prefix":"","firstName":"Mu","middleName":"","lastName":"yingxue","suffix":""},{"id":448590282,"identity":"323b4c30-14a8-466f-9143-a4d45b1be5eb","order_by":2,"name":"Wen Xiumei","email":"","orcid":"","institution":"Hebei University of Architecture","correspondingAuthor":false,"prefix":"","firstName":"Wen","middleName":"","lastName":"Xiumei","suffix":""},{"id":448590283,"identity":"d6b892ba-e102-40ae-b3f8-aa14cc4d31f3","order_by":3,"name":"Meng Fanxing","email":"","orcid":"","institution":"Hebei University of Architecture","correspondingAuthor":false,"prefix":"","firstName":"Meng","middleName":"","lastName":"Fanxing","suffix":""}],"badges":[],"createdAt":"2025-03-11 08:53:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6201452/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6201452/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":81575525,"identity":"292d9a92-0d81-4c21-80f4-c2b56d3d4132","added_by":"auto","created_at":"2025-04-28 17:31:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":627503,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscriptv2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6201452/v1_covered_03082836-e592-4f11-915f-9e0b8723936a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Self-Supervised Heterogeneous Graph Neural Network with Multi-Scale Meta-Path Contrastive Learning","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":"international-journal-of-computational-intelligence-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [International Journal of Computational Intelligence Systems](https://link.springer.com/journal/44196)","snPcode":"44196","submissionUrl":"https://submission.springernature.com/new-submission/44196/3","title":"International Journal of Computational Intelligence Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Heterogeneous Neural Networks, Self-Supervised Learning, Meta-Path, Star-Shaped Contrastive Loss Function, Contrastive Learning","lastPublishedDoi":"10.21203/rs.3.rs-6201452/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6201452/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eHeterogeneous graph neural networks (HGNNs) exhibit remarkable capabilities in modeling complex structures and multi-semantic information. However, existing methods mainly focus on capturing high-order association patterns between heterogeneous nodes when constructing meta-paths, while they often lack sufficient expressive power for local neighborhood information. This limitation hinders their ability to effectively model both global and local structural relationships. To address this issue, we propose a self-supervised heterogeneous graph neural network (HMMC) based on multi-scale meta-path contrastive learning. The proposed approach introduces a multi-scale meta-path embedding mechanism that jointly captures both local and global structural information. Additionally, we design a cross-view self-supervised contrastive learning framework to optimize representations across multiple views, thereby enhancing the model's capacity to represent heterogeneous graph topological structures. To effectively mitigate the negative sample noise that often interferes with model optimization in traditional contrastive learning methods, we propose a novel star-shaped contrastive loss. This loss function ensures the representational consistency of positive sample pairs by constructing a multi-level optimization strategy involving center nodes, positive samples, and negative samples. Experimental results show that the proposed method outperforms existing state-of-the-art approaches across multiple datasets, achieving performance improvements of 0.5\u0026ndash;4.1%, thus fully validating its representational capacity, robustness, and generalizability in heterogeneous graph learning tasks.\u003c/p\u003e","manuscriptTitle":"Self-Supervised Heterogeneous Graph Neural Network with Multi-Scale Meta-Path Contrastive Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-28 17:07:00","doi":"10.21203/rs.3.rs-6201452/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-05-27T21:20:37+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-14T16:39:05+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-04T12:27:58+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-05-04T05:42:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"170883181067073233954218862941663867993","date":"2025-04-27T04:26:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"81031817921089181933884757133670388998","date":"2025-04-27T01:22:32+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"322474048962345817793232632348513211079","date":"2025-04-25T10:38:44+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-25T10:34:16+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-03-15T05:56:03+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-03-14T12:43:44+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Computational Intelligence Systems","date":"2025-03-11T08:44:10+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-computational-intelligence-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [International Journal of Computational Intelligence Systems](https://link.springer.com/journal/44196)","snPcode":"44196","submissionUrl":"https://submission.springernature.com/new-submission/44196/3","title":"International Journal of Computational Intelligence Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"27814e2e-0598-428c-a730-8a495f7cf4aa","owner":[],"postedDate":"April 28th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-12-08T22:08:23+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-28 17:07:00","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6201452","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6201452","identity":"rs-6201452","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}