Debiased Recommendation Based on Comparative Learning and Causal Embedding

Debiased Recommendation Based on Comparative Learning and Causal Embedding | 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 Debiased Recommendation Based on Comparative Learning and Causal Embedding Dingyuan Liu, Yaling Xun, Xiaoying Hu, Yanfeng Li Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4593605/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 Biases in recommendation systems significantly reduce recommendation accuracy and user experience. To address the issues in traditional recommendation systems: (1) inaccurate recommendation results due to ineffective modeling of users’ long-term and short-term interests, (2) popularity bias caused by the conformity effect, a debias recommendation method based on contrastive learning and causal embedding (CLACE). CLACE first employs two independent encoders to model users’ long-term and short-term interests separately. Then, a contrastive learning framework is designed to supervise the similarity between the long-term and short-term interest representations and interest proxies. A dynamic attention mechanism is introduced to adaptively adjust the weights of long-term and short-term interests to accurately reflect users’ preference biases. Simultaneously, to fundamentally reduce the popularity bias induced by the conformity effect during the recommendation process, a causal embedding model is introduced to separate user interests from the conformity effect, eliminating the negative impact of the conformity effect on recommendation results and achieving more precise recommendations. The effectiveness of the proposed CLACE is validated on two public datasets, and experimental results demonstrate that CLACE significantly improves recommendation accuracy, recall, and normalized discounted cumulative gain. Recommendation System Bias Long-short term interest Contrastive Learning Causal Embedding 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-4593605","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":319923196,"identity":"d581bbd6-ffac-4510-b415-ddead16239ca","order_by":0,"name":"Dingyuan Liu","email":"","orcid":"","institution":"Taiyuan University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Dingyuan","middleName":"","lastName":"Liu","suffix":""},{"id":319923197,"identity":"64061259-a86d-44b1-ba4d-702616fd5d95","order_by":1,"name":"Yaling Xun","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA30lEQVRIiWNgGAWjYLCCh3/+ycHYjA1EaUlsOGDMA2IcIEVLYg/RWgxu5B6TSNxxJ32/RI7x5w8MNrIbDjA/e4BPi+SMvDSJxDPPcnskcswkDjCkGW84wGZugE8LP0hlAhszWAvQYYcTNxzgYZPAp4UNqiWdB+iwDwcY/hPWArYlse1wAlCLAdBhBwhrkex5Y2yRcCbNsOfMszKJMwbJxjMPs5nh1WJwPMfwxocKG3n29uTNHyoq7GT7jjc/w6sFCFggCgQSQCYAMTMB9SAlHyC+OkBY6SgYBaNgFIxMAACNAUq2U3mK1AAAAABJRU5ErkJggg==","orcid":"","institution":"Taiyuan University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Yaling","middleName":"","lastName":"Xun","suffix":""},{"id":319923198,"identity":"63998cff-7d29-4cd4-be63-591290d1ee58","order_by":2,"name":"Xiaoying Hu","email":"","orcid":"","institution":"Taiyuan University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Xiaoying","middleName":"","lastName":"Hu","suffix":""},{"id":319923199,"identity":"b3a016e4-0920-4c90-8faa-d6d9bc207f09","order_by":3,"name":"Yanfeng Li Li","email":"","orcid":"","institution":"Taiyuan University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Yanfeng","middleName":"Li","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2024-06-17 10:41:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4593605/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4593605/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100549098,"identity":"da08eeee-a018-40a3-adf2-ead5be5d5a52","added_by":"auto","created_at":"2026-01-19 08:22:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":486300,"visible":true,"origin":"","legend":"","description":"","filename":"ArticleTitle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4593605/v1_covered_54d3d0bf-3531-4c80-abb1-a70e3ef176dd.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Debiased Recommendation Based on Comparative Learning\nand Causal Embedding","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":"Recommendation System, Bias, Long-short term interest, Contrastive Learning, Causal Embedding","lastPublishedDoi":"10.21203/rs.3.rs-4593605/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4593605/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Biases in recommendation systems significantly reduce recommendation accuracy and user experience. To address the issues in traditional recommendation systems: (1) inaccurate recommendation results due to ineffective modeling of users’ long-term and short-term interests, (2) popularity bias caused by the conformity effect, a debias recommendation method based on contrastive learning and causal embedding (CLACE). CLACE first employs two independent encoders to model users’ long-term and short-term interests separately. Then, a contrastive learning framework is designed to supervise the similarity between the long-term and short-term interest representations and interest proxies. A dynamic attention mechanism is introduced to adaptively adjust the weights of long-term and short-term interests to accurately reflect users’ preference biases. Simultaneously, to fundamentally reduce the popularity bias induced by the conformity effect during the recommendation process, a causal embedding model is introduced to separate user interests from the conformity effect, eliminating the negative impact of the conformity effect on recommendation results and achieving more precise recommendations. The effectiveness of the proposed CLACE is validated on two public datasets, and experimental results demonstrate that CLACE significantly improves recommendation accuracy, recall, and normalized discounted cumulative gain.","manuscriptTitle":"Debiased Recommendation Based on Comparative Learning\nand Causal Embedding","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-08 05:44:06","doi":"10.21203/rs.3.rs-4593605/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":"23df9649-8400-48a4-98cf-f60e1c08bd4b","owner":[],"postedDate":"July 8th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-17T23:23:17+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-08 05:44:06","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4593605","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4593605","identity":"rs-4593605","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}