HSMGNN Hyperbolic S2 Rotation Group Multi-Channel Graph Neural Network for Cross-lingual Entity Alignment

HSMGNN Hyperbolic S2 Rotation Group Multi-Channel Graph Neural Network for Cross-lingual Entity Alignment | 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 HSMGNN Hyperbolic S 2 Rotation Group Multi-Channel Graph Neural Network for Cross-lingual Entity Alignment Yu Deng, ShiWang Hou, Mingyi Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6747285/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 10 You are reading this latest preprint version Abstract Entity alignment—a crucial task in knowledge graph research—is often hampered by the inherent heterogeneity between the graphs being aligned. These differences pose serious challenges for existing alignment methods, highlighting the need for more innovative and adaptable solutions.To address this, we propose a novel framework that integrates with graph neural networks: the Hyperbolic $\mathbb{S}^2$ Rotation Group in Multi-Channel Graph Neural Network (HSMGNN). HSMGNN is designed to effectively capture the diverse and complex structures of heterogeneous knowledge graphs, offering a streamlined and powerful approach to entity alignment.HSMGNN operates across multiple channels, each equipped with a distinct relation-weighting strategy for encoding knowledge graphs. One channel uses self-attention mechanisms to complete the knowledge graph by filling in missing data within each graph. Simultaneously, another channel applies cross-graph attention to pinpoint and filter out entities that are irrelevant to the alignment task. These diverse features are then aggregated using pooling techniques to form a unified, high-quality representation.What distinguishes HSMGNN is its ability to infer and transfer rule-based knowledge between graphs, ensuring coherent and consistent completion on both sides. This end-to-end framework not only boosts performance in entity alignment tasks but also bridges structural differences between heterogeneous graphs in a principled way.In short, HSMGNN marks a meaningful step forward in entity alignment, offering a robust, efficient, and scalable solution for aligning knowledge graphs in complex real-world scenarios. Biological sciences/Computational biology and bioinformatics/Data acquisition Biological sciences/Computational biology and bioinformatics/Data integration Biological sciences/Computational biology and bioinformatics/Data processing Biological sciences/Computational biology and bioinformatics/Databases Biological sciences/Computational biology and bioinformatics/Machine learning Biological sciences/Computational biology and bioinformatics/Software Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 20 Apr, 2026 Reviews received at journal 17 Apr, 2026 Reviewers agreed at journal 21 Mar, 2026 Reviews received at journal 01 Nov, 2025 Reviewers agreed at journal 17 Oct, 2025 Reviewers invited by journal 08 Oct, 2025 Editor assigned by journal 09 Sep, 2025 Editor invited by journal 16 Jun, 2025 Submission checks completed at journal 13 Jun, 2025 First submitted to journal 26 May, 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-6747285","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":531939265,"identity":"fe2ba82f-c367-4c04-9560-edac44b3c0ce","order_by":0,"name":"Yu Deng","email":"","orcid":"","institution":"University of Hunan Technology and Business","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Deng","suffix":""},{"id":531939266,"identity":"e37978b2-e3b0-409e-bfdc-43471f02f5cf","order_by":1,"name":"ShiWang Hou","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6UlEQVRIiWNgGAWjYBACAyBmBpMMzMeAxAEgTiBaC1saUDXRWsCAx4w4LebsPcafCwoOy5vzr/n2mPfHHQZ+9hwDhp87cGux7DljJj3D4LDhzhlvtxvzJDxjkOx5Y8DYewaPw27kmDHzGNxm3HDj7DZpnoTDIBEDZsY2vFqMPwO12G+4ceYZWIs9EVoMpIFaEjec72GD2CJBSMuZY2VALf+TN9xgM5Ock/aMR+LMs4KDvfi0HG/e/JnnT5rthvOHn0m8sbkjx9+evPHBTzxaEEAiAUzxgIgDxGhgYOAnUt0oGAWjYBSMPAAApfxUlyS7JZwAAAAASUVORK5CYII=","orcid":"","institution":"Huaihua University","correspondingAuthor":true,"prefix":"","firstName":"ShiWang","middleName":"","lastName":"Hou","suffix":""},{"id":531939267,"identity":"b73804cf-b4bb-41bf-9064-f29c92ec0c11","order_by":2,"name":"Mingyi Zhang","email":"","orcid":"","institution":"University of Hunan Technology and Business","correspondingAuthor":false,"prefix":"","firstName":"Mingyi","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2025-05-26 05:38:53","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6747285/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6747285/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94110396,"identity":"f9196dcf-c62d-4364-bb89-d6c5b1e1194a","added_by":"auto","created_at":"2025-10-22 13:11:40","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5368726,"visible":true,"origin":"","legend":"","description":"","filename":"main.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6747285/v1/551e9af5f3ea73c4be8b6884.pdf"},{"id":94110390,"identity":"9e0b78b0-c0cc-44bf-b24c-5b803e92ad0d","added_by":"auto","created_at":"2025-10-22 13:11:39","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6134,"visible":true,"origin":"","legend":"","description":"","filename":"c3310f8c6f624c749f269c239362d4c6.json","url":"https://assets-eu.researchsquare.com/files/rs-6747285/v1/c91b4a84c534a00fefd2c804.json"},{"id":94110665,"identity":"a13473f2-31e5-4e75-82ed-931cb7fa65d2","added_by":"auto","created_at":"2025-10-22 13:19:52","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6213662,"visible":true,"origin":"","legend":"","description":"","filename":"main.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6747285/v1_covered_68af441c-3c0f-4a71-9bd9-7cfdbf486b10.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eHSMGNN Hyperbolic S\u003csup\u003e2\u003c/sup\u003e Rotation Group Multi-Channel Graph Neural Network for Cross-lingual Entity Alignment\u003c/p\u003e","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-6747285/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6747285/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Entity alignment—a crucial task in knowledge graph research—is often hampered by the inherent heterogeneity between the graphs being aligned. These differences pose serious challenges for existing alignment methods, highlighting the need for more innovative and adaptable solutions.To address this, we propose a novel framework that integrates with graph neural networks: the Hyperbolic $\\mathbb{S}^2$ Rotation Group in Multi-Channel Graph Neural Network (HSMGNN). HSMGNN is designed to effectively capture the diverse and complex structures of heterogeneous knowledge graphs, offering a streamlined and powerful approach to entity alignment.HSMGNN operates across multiple channels, each equipped with a distinct relation-weighting strategy for encoding knowledge graphs. One channel uses self-attention mechanisms to complete the knowledge graph by filling in missing data within each graph. Simultaneously, another channel applies cross-graph attention to pinpoint and filter out entities that are irrelevant to the alignment task. These diverse features are then aggregated using pooling techniques to form a unified, high-quality representation.What distinguishes HSMGNN is its ability to infer and transfer rule-based knowledge between graphs, ensuring coherent and consistent completion on both sides. This end-to-end framework not only boosts performance in entity alignment tasks but also bridges structural differences between heterogeneous graphs in a principled way.In short, HSMGNN marks a meaningful step forward in entity alignment, offering a robust, efficient, and scalable solution for aligning knowledge graphs in complex real-world scenarios.","manuscriptTitle":"HSMGNN Hyperbolic S2 Rotation Group Multi-Channel Graph Neural Network for Cross-lingual Entity Alignment","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-22 13:11:35","doi":"10.21203/rs.3.rs-6747285/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-21T03:57:55+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-17T14:31:43+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"154687603568383685558480284324692176419","date":"2026-03-21T08:17:47+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-02T00:01:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"105180590394183226132843598159573452265","date":"2025-10-17T11:05:09+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-09T03:49:01+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-09T05:09:32+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-06-16T05:56:26+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-06-13T09:40:14+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-05-26T05:32:03+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"608ea665-abd9-4266-8748-9153794a0a30","owner":[],"postedDate":"October 22nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[{"id":56711500,"name":"Biological sciences/Computational biology and bioinformatics/Data acquisition"},{"id":56711501,"name":"Biological sciences/Computational biology and bioinformatics/Data integration"},{"id":56711502,"name":"Biological sciences/Computational biology and bioinformatics/Data processing"},{"id":56711503,"name":"Biological sciences/Computational biology and bioinformatics/Databases"},{"id":56711504,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":56711505,"name":"Biological sciences/Computational biology and bioinformatics/Software"}],"tags":[],"updatedAt":"2026-04-21T04:10:34+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-22 13:11:35","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6747285","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6747285","identity":"rs-6747285","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}