Adaptive Feedback Graph-Enhanced Network ForSocial Recommendation

Adaptive Feedback Graph-Enhanced Network ForSocial Recommendation | 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 Adaptive Feedback Graph-Enhanced Network ForSocial Recommendation Zhixin Lv, Xiangguo Zhao, Yongjiao Sun, Haojie Nie, Xin Bi, Anrui Han This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5497725/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 Social recommendation systems leverage social network data and graph models to enhance recommendation performance. Recent studies have highlighted the effectiveness of integrating social recommender systems with graph neural networks (GNNs). However, several critical challenges still remain: (i) most existing models tend to overlook previous mistakes, leading to repeated errors in future predictions, potentially causing local optima and preventing optimal performance; and (ii) basic sampling methods fail to capture the structural characteristics of graph data effectively, often leading to samples that are inadequate for model training needs. To address these challenges, we propose an A daptive F eedback G raph-Enhanced N etwork (AFGN) for social recommendation. While our approach is inspired by reinforcement learning, it differs by emphasizing the penalization of errors instead of relying on a reward function to reinforce correct behavior. This error-driven correction mechanism allows the model to learn from past mistakes and improve its predictive accuracy. Additionally, we introduce a novel and efficient, structure-aware graph-enhanced negative sampling method, which enhances the model's ability to capture the graph structure between users and items. Experiments on real-world datasets show that our method achieves significant improvements in recommendation accuracy over strong baselines. Social Recommendation Graph Neural Network Negative Sampling Adaptive Feedback Full Text Additional Declarations No competing interests reported. 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-5497725","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":382908292,"identity":"0fda5e16-5aba-4add-85c0-ed6398dc1336","order_by":0,"name":"Zhixin Lv","email":"","orcid":"","institution":"Northeastern University","correspondingAuthor":false,"prefix":"","firstName":"Zhixin","middleName":"","lastName":"Lv","suffix":""},{"id":382908294,"identity":"3b8c89f7-e037-4237-90cf-2feae249b623","order_by":1,"name":"Xiangguo Zhao","email":"data:image/png;base64,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","orcid":"","institution":"Northeastern University","correspondingAuthor":true,"prefix":"","firstName":"Xiangguo","middleName":"","lastName":"Zhao","suffix":""},{"id":382908296,"identity":"d1481cc2-d9f7-4986-a171-ce90a85f7db7","order_by":2,"name":"Yongjiao Sun","email":"","orcid":"","institution":"Northeastern University","correspondingAuthor":false,"prefix":"","firstName":"Yongjiao","middleName":"","lastName":"Sun","suffix":""},{"id":382908297,"identity":"31d169e2-1e35-4de9-8a95-1df971e1a3c9","order_by":3,"name":"Haojie Nie","email":"","orcid":"","institution":"Northeastern University","correspondingAuthor":false,"prefix":"","firstName":"Haojie","middleName":"","lastName":"Nie","suffix":""},{"id":382908299,"identity":"bcffd786-9555-4b9f-8ca1-c04ce0fb720e","order_by":4,"name":"Xin Bi","email":"","orcid":"","institution":"Northeastern University","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Bi","suffix":""},{"id":382908301,"identity":"e823760f-9956-4ab1-8e6f-a21b9b58612e","order_by":5,"name":"Anrui Han","email":"","orcid":"","institution":"Northeastern University","correspondingAuthor":false,"prefix":"","firstName":"Anrui","middleName":"","lastName":"Han","suffix":""}],"badges":[],"createdAt":"2024-11-21 12:08:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5497725/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5497725/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":70828933,"identity":"7a6401da-84a2-4237-a141-be5c0dd19d54","added_by":"auto","created_at":"2024-12-07 12:46:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":712035,"visible":true,"origin":"","legend":"","description":"","filename":"AFGN.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5497725/v1_covered_a1688d0e-5880-40ba-96d0-c896c7fb8e4f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Adaptive Feedback Graph-Enhanced Network ForSocial Recommendation","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Social Recommendation, Graph Neural Network, Negative Sampling, Adaptive Feedback","lastPublishedDoi":"10.21203/rs.3.rs-5497725/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5497725/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSocial recommendation systems leverage social network data and graph models to enhance recommendation performance. Recent studies have highlighted the effectiveness of integrating social recommender systems with graph neural networks (GNNs). However, several critical challenges still remain: (i) most existing models tend to overlook previous mistakes, leading to repeated errors in future predictions, potentially causing local optima and preventing optimal performance; and (ii) basic sampling methods fail to capture the structural characteristics of graph data effectively, often leading to samples that are inadequate for model training needs. To address these challenges, we propose an \u003cb\u003eA\u003c/b\u003edaptive \u003cb\u003eF\u003c/b\u003eeedback \u003cb\u003eG\u003c/b\u003eraph-Enhanced \u003cb\u003eN\u003c/b\u003eetwork (AFGN) for social recommendation. While our approach is inspired by reinforcement learning, it differs by emphasizing the penalization of errors instead of relying on a reward function to reinforce correct behavior. This error-driven correction mechanism allows the model to learn from past mistakes and improve its predictive accuracy. Additionally, we introduce a novel and efficient, structure-aware graph-enhanced negative sampling method, which enhances the model's ability to capture the graph structure between users and items. Experiments on real-world datasets show that our method achieves significant improvements in recommendation accuracy over strong baselines.\u003c/p\u003e","manuscriptTitle":"Adaptive Feedback Graph-Enhanced Network ForSocial Recommendation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-03 19:42:58","doi":"10.21203/rs.3.rs-5497725/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":"ae6c0c04-a164-49dc-8c22-986015518277","owner":[],"postedDate":"December 3rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-12-07T12:38:22+00:00","versionOfRecord":[],"versionCreatedAt":"2024-12-03 19:42:58","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5497725","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5497725","identity":"rs-5497725","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}