Unsupervised Inductive node representation learning for dynamic graphs

Unsupervised Inductive node representation learning for dynamic graphs | 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 Unsupervised Inductive node representation learning for dynamic graphs Wen-Gang Zhou, Khushnood Abbas This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3972512/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 19 Mar, 2025 Read the published version in IEEE Access → Version 1 posted You are reading this latest preprint version Abstract Graph-structured data is crucial for modeling complex real-world systems, but traditional machine learning struggles with non-Euclidean relationships inherent in graphs. Graph embedding techniques address this by creating fixed-dimensional vector representations of nodes, edges, or graphs, enabling diverse downstream tasks. However, existing approaches often focus on static graphs, limiting applicability in time-sensitive scenarios. To bridge this gap, our research proposes a novel node embedding method tailored for Discrete Time Dynamic Graphs (DTDGs). We introduce a framework for learning model parameters to generate embeddings at any time point inductively. Through extensive experiments, our model demonstrates superior performance over state-of-the-art static and dynamic embedding methods, highlighting its effectiveness and robustness. This advancement in dynamic graph representation learning holds promise for real-world applications, from biological proteinprotein interaction networks to large-scale human interaction networks. We provide publicly available code for reproducibility of our results https://github.com/khushnood/UnsupervisedInductiveNodeRepresentationForDynamicGraphs. Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Information technology Biological sciences/Biotechnology/Proteomics/Protein protein interaction networks Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 19 Mar, 2025 Read the published version in IEEE Access → Version 1 posted 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-3972512","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":273993146,"identity":"4b7263a0-f5ff-45c9-8016-0f7f4349209a","order_by":0,"name":"Wen-Gang Zhou","email":"","orcid":"","institution":"Zhoukou Normal University","correspondingAuthor":false,"prefix":"","firstName":"Wen-Gang","middleName":"","lastName":"Zhou","suffix":""},{"id":273993147,"identity":"6cd19b1e-23d5-420f-b638-dd95ed5fa58b","order_by":1,"name":"Khushnood Abbas","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEUlEQVRIiWNgGAWjYBACgxsMDMxg1gEGNhBDjoEHzGXGqcVwBpoWY4JajCXQtCQ2ENJiJt1j/Llwh40c3wHmZ48LaurS5/ecPSbBUGGd2MB+9gA2LTYyZ8ykZ55JM5Y8wGZuPOPY4dzG3r40CYYz6UDr8hKwapHIMWPmbTucuOEA0EYetgO5zfw8ZhKMQJEGCR4DrA6TyDH+DNHC/k2a519dOhtYyz/cWowlcgykIVp4zIAM5gQe3h6glgbcWgxnpJUBVQL9cpin3Hhm32HDGTxnjC0SjqUbt/HkYNVicCN5M9BhwBA73r7tccG3Onn5nhzDGx9qrGX72c9g1YIAKBGRAMRs+NWPglEwCkbBKMADAG8pV8+p0eCfAAAAAElFTkSuQmCC","orcid":"","institution":"Zhoukou Normal University","correspondingAuthor":true,"prefix":"","firstName":"Khushnood","middleName":"","lastName":"Abbas","suffix":""}],"badges":[],"createdAt":"2024-02-20 10:34:09","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-3972512/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3972512/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1109/ACCESS.2025.3553377","type":"published","date":"2025-03-20T00:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":81039847,"identity":"a0b1024d-30e2-48dc-9ef8-d8e3e2295c31","added_by":"auto","created_at":"2025-04-21 13:22:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":348395,"visible":true,"origin":"","legend":"","description":"","filename":"UnsupervisedNodeEmbeddingForDynamicGraphsScientificReports1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3972512/v1_covered_8baa36fd-9543-4046-9cb0-aa514d52d817.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Unsupervised Inductive node representation learning for dynamic graphs","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-3972512/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3972512/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eGraph-structured data is crucial for modeling complex real-world systems, but traditional machine learning struggles with\u003c/p\u003e\n\u003cp\u003enon-Euclidean relationships inherent in graphs. Graph embedding techniques address this by creating fixed-dimensional\u003c/p\u003e\n\u003cp\u003evector representations of nodes, edges, or graphs, enabling diverse downstream tasks. However, existing approaches often focus on static graphs, limiting applicability in time-sensitive scenarios. To bridge this gap, our research proposes a novel node embedding method tailored for Discrete Time Dynamic Graphs (DTDGs). We introduce a framework for learning model parameters to generate embeddings at any time point inductively. Through extensive experiments, our model demonstrates superior performance over state-of-the-art static and dynamic embedding methods, highlighting its effectiveness and robustness. This advancement in dynamic graph representation learning holds promise for real-world applications, from biological proteinprotein interaction networks to large-scale human interaction networks. We provide publicly available code for reproducibility of our results https://github.com/khushnood/UnsupervisedInductiveNodeRepresentationForDynamicGraphs.\u003c/p\u003e","manuscriptTitle":"Unsupervised Inductive node representation learning for dynamic graphs","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-02-22 03:04:00","doi":"10.21203/rs.3.rs-3972512/v1","editorialEvents":[{"type":"communityComments","content":1}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"3f03a41b-f15c-478f-b2ae-4352549fabe4","owner":[],"postedDate":"February 22nd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":28879131,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":28879132,"name":"Physical sciences/Mathematics and computing/Information technology"},{"id":28879133,"name":"Biological sciences/Biotechnology/Proteomics/Protein protein interaction networks"}],"tags":[],"updatedAt":"2025-04-21T13:22:02+00:00","versionOfRecord":{"articleIdentity":"rs-3972512","link":"https://doi.org/10.1109/ACCESS.2025.3553377","journal":{"identity":"ieee-access","isVorOnly":true,"title":"IEEE Access"},"publishedOn":"2025-03-20 00:00:00","publishedOnDateReadable":"March 20th, 2025"},"versionCreatedAt":"2024-02-22 03:04:00","video":"","vorDoi":"10.1109/ACCESS.2025.3553377","vorDoiUrl":"https://doi.org/10.1109/ACCESS.2025.3553377","workflowStages":[]},"version":"v1","identity":"rs-3972512","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3972512","identity":"rs-3972512","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}