Tuning Knowledge Graph  Embeddings in Clustering with LISE

Tuning Knowledge Graph Embeddings in Clustering with LISE | 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 Tuning Knowledge Graph Embeddings in Clustering with LISE Verdiana Schena, Simona Colucci, Donini Francesco Maria, Floriano Scioscia, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8250999/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 Background: Knowledge Graph Embeddings are increasingly used in biomedical informatics to support similarity assessment, clustering, and knowledge discovery. Despite strong performance in link prediction, recent studies show that numerical proximity in embedding spaces does not always reflect meaningful semantic similarity. LISE, a logic-based interactive similarity explainer, was introduced to expose shared semantic properties among clustered RDF resources and incorporate user feedback when evaluating cluster coherence. This work extends LISE by integrating Large Language Models for natural-language explanation and investigating whether user-derived relevance signals can actively influence embedding generation, improving the semantic adequacy of similarity-based clustering. Results: We replaced LISE’s template-based verbalization component with a Gemini 2.5 Flash module capable of generating human-readable, path-level explanations of logical Common Subsumers. This resolves previous LISE limitations related to granularity and anaphora resolution, enabling reliable sentence-level user evaluations. To assess whether user preferences can guide the embedding process, we simulated feedback on 1,280 DrugBank-derived triples and evaluated two custom pyRDF2Vec sampling strategies: Predicate Relevance Weight and Predicate-Object Relevance Weight. Relevance weights were learned via a random forest regressor trained on simulated user scores. Predicate-level weighting increased the presence of user-preferred predicates in the most cohesive clusters, with all predicates showing positive or neutral deviation under learned weights. By contrast, predicate-object weighting exhibited limited sensitivity, with most pairs showing unchanged frequency regardless of weight assignment. Average deviation metrics confirm that predicate-level adjustments redirect clustering more effectively toward semantically meaningful biomedical information. Conclusions: User-informed predicate weighting can successfully influence embedding-based clustering, improving alignment with semantically relevant biomedical properties. Predicate-object adjustments provide minimal benefit. Part of this research has been published in the proceedings of the 8th Workshop on Semantic Web Solutions for Large-scale Biomedical Data Analytics (SeWeBMeDA 2025). Knowledge Graph Embeddings Semantic Similarity Interactive Explainability RDF2Vec Clustering Large Language Models Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 17 Mar, 2026 Reviews received at journal 07 Mar, 2026 Reviewers agreed at journal 12 Feb, 2026 Reviews received at journal 29 Dec, 2025 Reviewers agreed at journal 15 Dec, 2025 Reviewers agreed at journal 10 Dec, 2025 Reviewers invited by journal 10 Dec, 2025 Editor assigned by journal 02 Dec, 2025 Submission checks completed at journal 02 Dec, 2025 First submitted to journal 01 Dec, 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-8250999","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":558375202,"identity":"636968c2-832b-4a78-a491-fee88d1a9a12","order_by":0,"name":"Verdiana Schena","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8UlEQVRIiWNgGAWjYJACZhDBz8DDIAGkZdhAZAIxWiQbIFp4IFoI6AFrMTgA1QIm8VljcID94eeCijvyxrd7D95g3GHDwyfd/IDh4Q98WniMpWeceWa47c65ZAvGM2k8bDLHDPA6DOgFNmbetsOM227kmEkwth0G+iWBkBb2Z8y8/w7bb54B15L+Aa8WfgYGM2behsOJGyTgWnLw28LPDPQLz7HDyTPunDG2SAT75UzBgYQ03FrY2NsffuapOWzbP7vH8MbHHTZy8rPbNz78YYNbCyRSQAAUHYkNEPYBPBqQAEgLYwNxakfBKBgFo2BkAQDMm0lXpWh8dgAAAABJRU5ErkJggg==","orcid":"","institution":"Polytechnic University of Bari","correspondingAuthor":true,"prefix":"","firstName":"Verdiana","middleName":"","lastName":"Schena","suffix":""},{"id":558375206,"identity":"e48198df-5bd7-44e3-be58-36aea35f6283","order_by":1,"name":"Simona Colucci","email":"","orcid":"","institution":"Polytechnic University of Bari","correspondingAuthor":false,"prefix":"","firstName":"Simona","middleName":"","lastName":"Colucci","suffix":""},{"id":558375207,"identity":"01b3989d-6368-409a-b7a2-5e369d196a62","order_by":2,"name":"Donini Francesco Maria","email":"","orcid":"","institution":"Tuscia University","correspondingAuthor":false,"prefix":"","firstName":"Donini","middleName":"Francesco","lastName":"Maria","suffix":""},{"id":558375208,"identity":"1110f2da-a419-4e88-8902-99cccb3c35c8","order_by":3,"name":"Floriano Scioscia","email":"","orcid":"","institution":"Polytechnic University of Bari","correspondingAuthor":false,"prefix":"","firstName":"Floriano","middleName":"","lastName":"Scioscia","suffix":""},{"id":558375209,"identity":"4b078689-8155-40b2-9464-2d8da6df1a38","order_by":4,"name":"Eugenio Di Sciascio","email":"","orcid":"","institution":"Polytechnic University of Bari","correspondingAuthor":false,"prefix":"","firstName":"Eugenio","middleName":"Di","lastName":"Sciascio","suffix":""}],"badges":[],"createdAt":"2025-12-01 13:38:37","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8250999/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8250999/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98198554,"identity":"ef1ccbac-8ea4-426f-9beb-3841f483dd41","added_by":"auto","created_at":"2025-12-15 07:16:31","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7647,"visible":true,"origin":"","legend":"","description":"","filename":"25f1717895b4440db2cc92eb22ac4d3f.json","url":"https://assets-eu.researchsquare.com/files/rs-8250999/v1/a5d604a8330c0733b1447581.json"},{"id":98198555,"identity":"e8e410f7-1167-4886-9875-053ae32081c5","added_by":"auto","created_at":"2025-12-15 07:16:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":672776,"visible":true,"origin":"","legend":"","description":"","filename":"JBS2025.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8250999/v1_covered_5307464b-d936-44a6-a484-6f46214e7141.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Tuning Knowledge Graph Embeddings in Clustering with LISE","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"journal-of-biomedical-semantics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jbsm","sideBox":"Learn more about [Journal of Biomedical Semantics](http://jbiomedsem.biomedcentral.com/)","snPcode":"13326","submissionUrl":"https://submission.nature.com/new-submission/13326/3","title":"Journal of Biomedical Semantics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Knowledge Graph Embeddings, Semantic Similarity, Interactive Explainability, RDF2Vec, Clustering, Large Language Models","lastPublishedDoi":"10.21203/rs.3.rs-8250999/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8250999/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBackground: Knowledge Graph Embeddings \u0026nbsp;are increasingly used in biomedical informatics to support similarity assessment, clustering, and knowledge discovery. Despite strong performance in link prediction, recent studies show that numerical proximity in embedding spaces does not always reflect meaningful semantic similarity. LISE, a logic-based interactive similarity explainer, was introduced to expose shared semantic properties among clustered RDF resources and incorporate user feedback when evaluating cluster coherence. This work extends LISE by integrating Large Language Models for natural-language explanation and investigating whether user-derived relevance signals can actively influence embedding generation, improving the semantic adequacy of similarity-based clustering.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eResults: We replaced\u0026nbsp; LISE’s template-based verbalization component with a Gemini 2.5 Flash module capable of generating human-readable, path-level explanations of logical Common Subsumers. This resolves previous LISE limitations related to granularity and anaphora resolution, enabling reliable sentence-level user evaluations. To assess whether user preferences can guide the embedding process, we simulated feedback on 1,280 DrugBank-derived triples and evaluated two custom pyRDF2Vec sampling strategies: Predicate Relevance Weight and Predicate-Object Relevance Weight. Relevance weights were learned via a random forest regressor trained on simulated user scores. Predicate-level weighting increased the presence of user-preferred predicates in the most cohesive clusters, with all predicates showing positive or neutral deviation under learned weights. By contrast, predicate-object weighting exhibited limited sensitivity, with most pairs showing unchanged frequency regardless of weight assignment. Average deviation metrics confirm that predicate-level adjustments redirect clustering more effectively toward semantically meaningful biomedical information.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eConclusions: User-informed predicate weighting can successfully influence embedding-based clustering, improving alignment with semantically relevant biomedical properties. Predicate-object adjustments provide minimal benefit. Part of this research has been published in the proceedings of the 8th Workshop on Semantic Web Solutions for Large-scale Biomedical Data Analytics (SeWeBMeDA 2025).\u0026nbsp;\u003c/p\u003e","manuscriptTitle":"Tuning Knowledge Graph Embeddings in Clustering with LISE","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-15 07:16:25","doi":"10.21203/rs.3.rs-8250999/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-17T18:56:17+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-07T23:17:10+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"170120319831077721559476567411345967785","date":"2026-02-12T15:15:10+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-29T15:48:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"293219766611205947424609748701096994305","date":"2025-12-16T03:00:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"224769050618569802457250683651172737255","date":"2025-12-10T14:50:28+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-12-10T08:58:14+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-12-02T14:34:19+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-12-02T14:31:12+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Biomedical Semantics","date":"2025-12-01T13:30:15+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-biomedical-semantics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jbsm","sideBox":"Learn more about [Journal of Biomedical Semantics](http://jbiomedsem.biomedcentral.com/)","snPcode":"13326","submissionUrl":"https://submission.nature.com/new-submission/13326/3","title":"Journal of Biomedical Semantics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"450aa631-3517-42db-b3e3-97b4bddd9b06","owner":[],"postedDate":"December 15th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-21T12:23:16+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-15 07:16:25","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8250999","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8250999","identity":"rs-8250999","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}