Personalized Conformity Disentanglement for Debiased Recommendations

Personalized Conformity Disentanglement for Debiased Recommendations | 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 Personalized Conformity Disentanglement for Debiased Recommendations haichao zhang, Yongfei Ye, Chong Zhang, Jia Wang, Qinyao Liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9233874/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 8 You are reading this latest preprint version Abstract Traditional recommender systems often focus on spurious correlations between user/item profiles and interaction predictions, while ignoring the hidden confounding factors, such as user conformity. It affects both the item's popularity and the ratings. Item popularity can introduce popularity bias in observed interactions, affecting recommendation systems. Existing methods typically address this bias from a causal perspective. The item's popularity corresponds to the treatment, while the ratings equate to the outcome within the causal inference framework. However, we argue that popularity bias is personalized, necessitating a personalized approach to debiasing. In this work, we propose PCDR, a personalized causal disentanglement for debiasing recommendation. We analyze the causality behind the interaction between the users and employ multiple encoders to assign different representations to users. To further enhance this distinction, we apply contrastive learning to separate user conformity levels across different popular items. To validate the effectiveness of PCDR, we performed experiments on three real-world datasets (ML-1M, Netflix, and Amazon). Our results demonstrate significant improvements over state-of-the-art models in three evaluation metrics: Recall (34.59% improvement), NDCG (21.00% improvement), and HR (27.50% improvement). The source code is available at: https://anonymous.4open.science/r/PCDR . Recommendation system Popularity bias Causal embedding Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 30 Apr, 2026 Reviewers agreed at journal 29 Apr, 2026 Reviewers agreed at journal 22 Apr, 2026 Reviewers agreed at journal 08 Apr, 2026 Reviewers invited by journal 06 Apr, 2026 Editor assigned by journal 01 Apr, 2026 Submission checks completed at journal 27 Mar, 2026 First submitted to journal 26 Mar, 2026 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-9233874","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":619456438,"identity":"7dd82504-484f-4a06-997b-b877d5a77828","order_by":0,"name":"haichao zhang","email":"","orcid":"","institution":"Xi’an Jiaotong-Liverpool University","correspondingAuthor":false,"prefix":"","firstName":"haichao","middleName":"","lastName":"zhang","suffix":""},{"id":619456439,"identity":"10e7096f-eb6d-4220-bd17-e65832f0a9a5","order_by":1,"name":"Yongfei Ye","email":"","orcid":"","institution":"China United Network Communications Group Co","correspondingAuthor":false,"prefix":"","firstName":"Yongfei","middleName":"","lastName":"Ye","suffix":""},{"id":619456440,"identity":"d80febf0-f1e6-471a-9bc7-a5a40c8ea2ee","order_by":2,"name":"Chong Zhang","email":"","orcid":"","institution":"Xi’an Jiaotong-Liverpool University","correspondingAuthor":false,"prefix":"","firstName":"Chong","middleName":"","lastName":"Zhang","suffix":""},{"id":619456441,"identity":"e35da923-6ae0-4f86-a2af-8e764e07d000","order_by":3,"name":"Jia Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABBklEQVRIiWNgGAWjYBAC9mYog429+QCDBIMFiG2AVwsjTAs/z7EEBokECSK0NEAZkjNygCqJ0tLO/ICZp+aO3YYDOd8kLH9IJDawN2+TYKi5g8dhbAbMPMeeJW84cHazAdBhiQ08x8okGI49w+cXA+YctsPJBgd7Nz4Aa5HIMZNgbDiMRwv7B+acf0Ath3keHABrkX+DX4tgM48Bc27bYTvJNh5GqC08+LVIM/MUHP7bdziBn4fN2EAiTcK4jSet2CLhGG4tfPzHNz6c8e2wPZv842fSEjY2sv3shzfe+FCDWwsIHADixAYgwQyKFTaQUAJeDRBgDyIYPxChchSMglEwCkYeAAA0sFC8ztRFiAAAAABJRU5ErkJggg==","orcid":"","institution":"Xi’an Jiaotong-Liverpool University","correspondingAuthor":true,"prefix":"","firstName":"Jia","middleName":"","lastName":"Wang","suffix":""},{"id":619456442,"identity":"89fc3627-4c07-442d-b804-9b6bd9975cdc","order_by":4,"name":"Qinyao Liu","email":"","orcid":"","institution":"Xi’an Jiaotong-Liverpool University","correspondingAuthor":false,"prefix":"","firstName":"Qinyao","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2026-03-26 12:08:24","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9233874/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9233874/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106725661,"identity":"a9517be2-3552-46c9-b519-87d144204fea","added_by":"auto","created_at":"2026-04-12 18:33:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1086464,"visible":true,"origin":"","legend":"","description":"","filename":"JMLCPCDR.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9233874/v1_covered_73499caa-8f38-45a2-85c1-765536ce73c9.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Personalized Conformity Disentanglement for Debiased Recommendations","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":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Recommendation system, Popularity bias, Causal embedding","lastPublishedDoi":"10.21203/rs.3.rs-9233874/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9233874/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Traditional recommender systems often focus on spurious correlations between user/item profiles and interaction predictions, while ignoring the hidden confounding factors, such as user conformity. It affects both the item's popularity and the ratings. Item popularity can introduce popularity bias in observed interactions, affecting recommendation systems. Existing methods typically address this bias from a causal perspective. The item's popularity corresponds to the treatment, while the ratings equate to the outcome within the causal inference framework. However, we argue that popularity bias is personalized, necessitating a personalized approach to debiasing. In this work, we propose PCDR, a personalized causal disentanglement for debiasing recommendation. We analyze the causality behind the interaction between the users and employ multiple encoders to assign different representations to users. To further enhance this distinction, we apply contrastive learning to separate user conformity levels across different popular items. To validate the effectiveness of PCDR, we performed experiments on three real-world datasets (ML-1M, Netflix, and Amazon). Our results demonstrate significant improvements over state-of-the-art models in three evaluation metrics: Recall (34.59% improvement), NDCG (21.00% improvement), and HR (27.50% improvement). The source code is available at: https://anonymous.4open.science/r/PCDR.","manuscriptTitle":"Personalized Conformity Disentanglement for Debiased Recommendations","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-10 03:48:17","doi":"10.21203/rs.3.rs-9233874/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-04-30T07:52:01+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"323715051363255067251285513541317582862","date":"2026-04-29T10:13:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"20650814852462086147052065289103182499","date":"2026-04-22T04:40:47+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"301349695345461516131185881813374214953","date":"2026-04-08T07:43:45+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-06T05:42:05+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-01T04:36:21+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-27T07:50:23+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Machine Learning and Cybernetics","date":"2026-03-26T11:54:59+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"76a78ee1-c0c4-4573-9d64-587f69ddfce3","owner":[],"postedDate":"April 10th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-04-30T07:52:01+00:00","index":58,"fulltext":""},{"type":"reviewerAgreed","content":"323715051363255067251285513541317582862","date":"2026-04-29T10:13:36+00:00","index":56,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-10T03:48:17+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-10 03:48:17","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9233874","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9233874","identity":"rs-9233874","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}