Uniform Regularization and Constrative Learning to Mitigate the Long-Tail Effect of Recommendation Algorithms

Uniform Regularization and Constrative Learning to Mitigate the Long-Tail Effect of Recommendation Algorithms | 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 Uniform Regularization and Constrative Learning to Mitigate the Long-Tail Effect of Recommendation Algorithms Xin Xie, Hanxin Zheng, Kexuan Liu, Xingpeng Zheng, Xuebo Cheng, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5674769/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 9 You are reading this latest preprint version Abstract In recommender systems, Graph Collaborative Filtering (GCF) is widely used for its ability to effectively model the interaction between users and items. However, in practical scenarios, GCF faces a significant problem: the representation of popular items tends to be over-concentrated, while cold items are marginalized, leading to recommendation results biased towards popular items and making it difficult to address the issue of long-tail distribution. To alleviate data sparsity, existing GCF methods typically incorporate Contrastive Learning (CL) to assist in updating node representations. However, inappropriate CL methods can introduce extra noise. For this reason, this paper proposes an Enhanced Contrastive Learning-based Graph Collaborative Filtering (ECL-GCF). The model improves the traditional GCF approach by: 1. capturing explicit interaction information between users and items by exploiting structural neighborhood contrastive learning; 2. introducing semantic neighborhood contrastive learning to construct potential similarity relationships by capturing implicit semantic information of users and items, thereby providing more meaningful representations for cold items; and 3. optimizing the embedding representation by regularizing chi-square and homogeneous embedding representations, ensuring that the embeddings are both close to positive sample pairs and uniformly distributed in the space, thus preventing the marginalization of cold items. Experimental results indicate that the model improves recommendation performance by approximately 5% on the Yelp2018 and iFashion datasets, and especially performs well on cold item recommendation. Recommender System Collaborative Filtering Contrastive Learning Graph Neural Network long-tail distribution Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 04 May, 2025 Reviews received at journal 23 Jan, 2025 Reviewers agreed at journal 14 Jan, 2025 Reviewers agreed at journal 13 Jan, 2025 Reviewers agreed at journal 26 Dec, 2024 Reviewers invited by journal 26 Dec, 2024 Editor assigned by journal 25 Dec, 2024 Submission checks completed at journal 25 Dec, 2024 First submitted to journal 19 Dec, 2024 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-5674769","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":394532228,"identity":"5aa19446-cca2-4d57-8a78-7f5e0ae0997f","order_by":0,"name":"Xin Xie","email":"","orcid":"","institution":"East China Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Xie","suffix":""},{"id":394532229,"identity":"92be0124-a3ce-4cb0-9543-bcaa5fc9e494","order_by":1,"name":"Hanxin Zheng","email":"data:image/png;base64,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","orcid":"","institution":"East China Jiaotong University","correspondingAuthor":true,"prefix":"","firstName":"Hanxin","middleName":"","lastName":"Zheng","suffix":""},{"id":394532230,"identity":"fce3637f-451a-443c-9348-b854b2653ad0","order_by":2,"name":"Kexuan Liu","email":"","orcid":"","institution":"East China Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Kexuan","middleName":"","lastName":"Liu","suffix":""},{"id":394532231,"identity":"23c4f389-f40f-4520-be80-8db42b396583","order_by":3,"name":"Xingpeng Zheng","email":"","orcid":"","institution":"East China Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Xingpeng","middleName":"","lastName":"Zheng","suffix":""},{"id":394532232,"identity":"ae4cb362-0d01-400c-b858-0a61b985a2e5","order_by":4,"name":"Xuebo Cheng","email":"","orcid":"","institution":"East China Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Xuebo","middleName":"","lastName":"Cheng","suffix":""},{"id":394532233,"identity":"d7531a5d-bf76-4ef2-a6e5-e531f2867cd7","order_by":5,"name":"Tao Wan","email":"","orcid":"","institution":"East China Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Tao","middleName":"","lastName":"Wan","suffix":""}],"badges":[],"createdAt":"2024-12-19 08:08:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5674769/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5674769/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":72390077,"identity":"86187aab-d72d-40f7-b2e7-4c3761fdb323","added_by":"auto","created_at":"2024-12-26 11:07:25","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":539245,"visible":true,"origin":"","legend":"","description":"","filename":"UniformRegularizationandConstrativeLearningtoMitigatetheLongTailEffectofRecommendationAlgorithms.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5674769/v1_covered_83eef761-41a2-45ec-9d59-bc26c83ce7b4.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Uniform Regularization and Constrative Learning to Mitigate the Long-Tail Effect of Recommendation Algorithms","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"cluster-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Cluster Computing](https://www.springer.com/journal/10586)","snPcode":"10586","submissionUrl":"https://submission.nature.com/new-submission/10586/3","title":"Cluster Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Recommender System, Collaborative Filtering, Contrastive Learning, Graph Neural Network, long-tail distribution","lastPublishedDoi":"10.21203/rs.3.rs-5674769/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5674769/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn recommender systems, Graph Collaborative Filtering (GCF) is widely used for its ability to effectively model the interaction between users and items. However, in practical scenarios, GCF faces a significant problem: the representation of popular items tends to be over-concentrated, while cold items are marginalized, leading to recommendation results biased towards popular items and making it difficult to address the issue of long-tail distribution. To alleviate data sparsity, existing GCF methods typically incorporate Contrastive Learning (CL) to assist in updating node representations. However, inappropriate CL methods can introduce extra noise. For this reason, this paper proposes an Enhanced Contrastive Learning-based Graph Collaborative Filtering (ECL-GCF). The model improves the traditional GCF approach by: 1. capturing explicit interaction information between users and items by exploiting structural neighborhood contrastive learning; 2. introducing semantic neighborhood contrastive learning to construct potential similarity relationships by capturing implicit semantic information of users and items, thereby providing more meaningful representations for cold items; and 3. optimizing the embedding representation by regularizing chi-square and homogeneous embedding representations, ensuring that the embeddings are both close to positive sample pairs and uniformly distributed in the space, thus preventing the marginalization of cold items. Experimental results indicate that the model improves recommendation performance by approximately 5% on the Yelp2018 and iFashion datasets, and especially performs well on cold item recommendation.\u003c/p\u003e","manuscriptTitle":"Uniform Regularization and Constrative Learning to Mitigate the Long-Tail Effect of Recommendation Algorithms","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-26 10:51:20","doi":"10.21203/rs.3.rs-5674769/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-05-04T17:18:26+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-01-23T19:41:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"280317539334891312320559629824297519342","date":"2025-01-14T23:18:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"106656563400618239641414788391514539139","date":"2025-01-13T06:24:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"134541968355336430403792277691264926069","date":"2024-12-26T08:18:42+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-12-26T06:15:15+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-12-25T11:51:41+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-12-25T09:40:02+00:00","index":"","fulltext":""},{"type":"submitted","content":"Cluster Computing","date":"2024-12-19T08:02:57+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"cluster-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Cluster Computing](https://www.springer.com/journal/10586)","snPcode":"10586","submissionUrl":"https://submission.nature.com/new-submission/10586/3","title":"Cluster Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"5821eb97-82a7-4190-93b3-02796a14c284","owner":[],"postedDate":"December 26th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-07-29T14:53:21+00:00","versionOfRecord":[],"versionCreatedAt":"2024-12-26 10:51:20","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5674769","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5674769","identity":"rs-5674769","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}