Cross-modal Transfer Learning from Tabular to Time Series Data via Semantic and Dynamic Temporal Graph Modeling

Cross-modal Transfer Learning from Tabular to Time Series Data via Semantic and Dynamic Temporal Graph Modeling | 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 Cross-modal Transfer Learning from Tabular to Time Series Data via Semantic and Dynamic Temporal Graph Modeling Wuman Luo, yuejing zhai, Yiping Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7146643/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Accurate time series modeling plays a critical role in health, financial, and industrial applications. However, real-world deployment faces two key issues: (1) scarcity of clean training data, and (2) valuable information is locked in structured tabular formats, and cannot be imported into time series models. These limitations significantly constrain prediction performance in time series tasks. Cross-modal transfer learning (CMTL) provides a possible solution. Existing CMTL approaches succeed with image, text, and audio data by leveraging their inherent local correlations and hierarchical structures. However, tabular data presents unique difficulties. Specifically, the discrete, heterogeneous nature of tabular features, and lack of explicit temporal relationships in columns, prevent direct geometric alignment with time series waveforms. In fact, although it has no temporal nature, tabular data still contains rich domain knowledge that can be used by time series tasks. In this paper, we propose a cross-modal transfer learning (CMTL) model from tabular to time series data, called TSgraph. TSgraph first extracts the domain topology and feature interaction paradigm from tabular data, and constructs it as a graph structure. Then, the time series graph of each time step is dynamically updated in combination with these graphs, and finally get the classification results. We validate the performance of TSgraph on four real-world datasets from different domains and compare the results with state-of-the-art baseline models. Experiments show that our model achieves the best performance on multiple evaluation metrics. Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Information technology Physical sciences/Mathematics and computing/Computational science Cross-modal Transfer Learning Time Series Graph neural network Full Text Additional Declarations There is NO Competing Interest. Cite Share Download PDF Status: Posted 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-7146643","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":489751750,"identity":"046c3d18-1713-49ce-a6bf-02bb77c51f11","order_by":0,"name":"Wuman Luo","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwElEQVRIiWNgGAWjYBACPhiDH0IxE9bCBmNINpCsxeAA0Vokko9J8+bY5RlfO3tMgqHCOrFB7PABAlrS0qR5tyUXm93OS5NgOJOe2CCdlkBAS47Zbd5tzInbbueYSTC2HQZqyTEgRkt94ubZIC3/iNdyOHGDNEhLAzFaeJ6l/5y77XjijNt5yRYJx9KN2wj5hZ89+bDB223Vif2zcw/e+FBjLdsvnXwArxYkwMPAADKejZA6VC2jYBSMglEwCrABAGl6P8YXEy8MAAAAAElFTkSuQmCC","orcid":"","institution":"Macao Polytechnic University","correspondingAuthor":true,"prefix":"","firstName":"Wuman","middleName":"","lastName":"Luo","suffix":""},{"id":489751751,"identity":"f0f1b15f-92fb-49b0-8c72-95a4e13fb254","order_by":1,"name":"yuejing zhai","email":"","orcid":"https://orcid.org/0000-0001-7877-2375","institution":"Macao Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"yuejing","middleName":"","lastName":"zhai","suffix":""},{"id":489751752,"identity":"986f6182-47a3-4cd2-871c-cfe3d3b4e1a4","order_by":2,"name":"Yiping Li","email":"","orcid":"","institution":"Macau University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Yiping","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-07-17 08:30:47","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7146643/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7146643/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105904012,"identity":"2e6f6970-9aa8-413f-9b4d-2908517144db","added_by":"auto","created_at":"2026-04-01 10:00:33","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4520997,"visible":true,"origin":"","legend":"Article File","description":"","filename":"NCTSgraph.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7146643/v1_covered_a2b67d0a-837f-446b-ad0f-255974088b3a.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Cross-modal Transfer Learning from Tabular to Time Series Data via Semantic and Dynamic Temporal Graph Modeling","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"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":"Cross-modal Transfer Learning, Time Series, Graph neural network","lastPublishedDoi":"10.21203/rs.3.rs-7146643/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7146643/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate time series modeling plays a critical role in health, financial, and industrial applications. However, real-world deployment faces two key issues: (1) scarcity of clean training data, and (2) valuable information is locked in structured tabular formats, and cannot be imported into time series models. These limitations significantly constrain prediction performance in time series tasks. Cross-modal transfer learning (CMTL) provides a possible solution. Existing CMTL approaches succeed with image, text, and audio data by leveraging their inherent local correlations and hierarchical structures. However, tabular data presents unique difficulties. Specifically, the discrete, heterogeneous nature of tabular features, and lack of explicit temporal relationships in columns, prevent direct geometric alignment with time series waveforms. In fact, although it has no temporal nature, tabular data still contains rich domain knowledge that can be used by time series tasks. In this paper, we propose a cross-modal transfer learning (CMTL) model from tabular to time series data, called TSgraph. TSgraph first extracts the domain topology and feature interaction paradigm from tabular data, and constructs it as a graph structure. Then, the time series graph of each time step is dynamically updated in combination with these graphs, and finally get the classification results. We validate the performance of TSgraph on four real-world datasets from different domains and compare the results with state-of-the-art baseline models. Experiments show that our model achieves the best performance on multiple evaluation metrics.","manuscriptTitle":"Cross-modal Transfer Learning from Tabular to Time Series Data via Semantic and Dynamic Temporal Graph Modeling","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-24 08:03:59","doi":"10.21203/rs.3.rs-7146643/v1","editorialEvents":[{"type":"communityComments","content":0}],"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":"fd181212-8117-49f3-bb1a-b92612b2680b","owner":[],"postedDate":"July 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":51996422,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":51996423,"name":"Physical sciences/Mathematics and computing/Information technology"},{"id":51996424,"name":"Physical sciences/Mathematics and computing/Computational science"}],"tags":[],"updatedAt":"2026-03-30T14:00:43+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-24 08:03:59","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7146643","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7146643","identity":"rs-7146643","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}