Stochastic Optimal Transport for Fair Representation Learning in Imbalanced Data Regimes

Stochastic Optimal Transport for Fair Representation Learning in Imbalanced Data Regimes | 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 Stochastic Optimal Transport for Fair Representation Learning in Imbalanced Data Regimes Jiahao Liang, Meilin Xu, Yuhang Chen, Fanyue Wu, Zhou Shen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8208943/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 In this paper, we propose a novel framework for achieving fair representation learning from imbalanced datasets using stochastic optimal transport (OT) theory. Recognizing the detrimental effects of data imbalance on predictive accuracy and fairness, we formulate an optimization problem that integrates fairness constraints with the mathematical principles of optimal transport. By leveraging Wasserstein barycenters, our approach is designed to produce latent representations that maintain demographic parity and equal opportunity, effectively mitigating bias against underrepresented groups. We provide a comprehensive theoretical analysis demonstrating the convergence properties of our method and establish fairness bounds that highlight its effectiveness. Empirical evaluations across diverse datasets, including the Adult Income and COMPAS datasets, exemplify our method's superiority over state-of-the-art techniques in reducing bias while preserving predictive performance. Our findings underscore the critical importance of incorporating fairness into representation learning frameworks and pave the way for future research in equitable AI systems. This work contributes a robust methodology that can enhance fairness in various applications, reinforcing a commitment to ethical standards in artificial intelligence. optimal transport fairness representation learning imbalanced data Wasserstein barycenter stochastic optimization Full Text Additional Declarations The authors declare no competing interests. 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-8208943","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":550931032,"identity":"d039389a-2378-411f-8f5b-8cca279baf26","order_by":0,"name":"Jiahao Liang","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Jiahao","middleName":"","lastName":"Liang","suffix":""},{"id":550931033,"identity":"75c6635e-0e40-4e0a-b91d-51f4bdcd4f65","order_by":1,"name":"Meilin Xu","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Meilin","middleName":"","lastName":"Xu","suffix":""},{"id":550931034,"identity":"9a2f045d-f0df-4651-8ef3-7508b3056dc0","order_by":2,"name":"Yuhang Chen","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Yuhang","middleName":"","lastName":"Chen","suffix":""},{"id":550931035,"identity":"f14f8cce-8ba4-4c64-b5ba-fcd722f9cc20","order_by":3,"name":"Fanyue Wu","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Fanyue","middleName":"","lastName":"Wu","suffix":""},{"id":550931036,"identity":"be7c453b-6b26-49ee-8970-d555ea526787","order_by":4,"name":"Zhou Shen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFElEQVRIiWNgGAWjYDACCSBmbEASMGAH8QwsSNHCcwBESpCiRSIBJo4dyM9uPvbw5w6bxAbpw4c/fKi5J28u+fzqhh8FEgz87d0J2LQY3DmWbiB5Ji2xgS8tTXLGsWLDnbNzym72AB0mcebsBqxaJHLMJAzbDic28PCYMfOwJSQY3M5Ju8ED1GIgkYtVi/yM/G8SiWAt/J8///kH1HLzTNrNP3i0MNzIYZM4CLGFQZqxDajlBvux2/hsMbiRZibZ2JZm3MbDZibZ25dguOFMDtttGQMJHlx+kZ+R/EzyZ5uNbD8P8+MPP74lyBscP/7s5ps/NnL87b3YHQYDbAgmjwGYxKscDbA/IEX1KBgFo2AUDH8AAA8DYpsNUdNBAAAAAElFTkSuQmCC","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Zhou","middleName":"","lastName":"Shen","suffix":""}],"badges":[],"createdAt":"2025-11-26 05:40:49","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8208943/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8208943/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96883005,"identity":"72b16a3d-c1d0-4f31-b52e-c37346ce2b77","added_by":"auto","created_at":"2025-11-27 07:35:39","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":225341,"visible":true,"origin":"","legend":"","description":"","filename":"paper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8208943/v1_covered_15da4716-2822-4e73-82a7-a62ec9d36def.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eStochastic Optimal Transport for Fair Representation Learning in Imbalanced Data Regimes\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"optimal transport, fairness, representation learning, imbalanced data, Wasserstein barycenter, stochastic optimization","lastPublishedDoi":"10.21203/rs.3.rs-8208943/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8208943/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn this paper, we propose a novel framework for achieving fair representation learning from imbalanced datasets using stochastic optimal transport (OT) theory. Recognizing the detrimental effects of data imbalance on predictive accuracy and fairness, we formulate an optimization problem that integrates fairness constraints with the mathematical principles of optimal transport. By leveraging Wasserstein barycenters, our approach is designed to produce latent representations that maintain demographic parity and equal opportunity, effectively mitigating bias against underrepresented groups. We provide a comprehensive theoretical analysis demonstrating the convergence properties of our method and establish fairness bounds that highlight its effectiveness. Empirical evaluations across diverse datasets, including the Adult Income and COMPAS datasets, exemplify our method's superiority over state-of-the-art techniques in reducing bias while preserving predictive performance. Our findings underscore the critical importance of incorporating fairness into representation learning frameworks and pave the way for future research in equitable AI systems. This work contributes a robust methodology that can enhance fairness in various applications, reinforcing a commitment to ethical standards in artificial intelligence.\u003c/p\u003e","manuscriptTitle":"Stochastic Optimal Transport for Fair Representation Learning in Imbalanced Data Regimes","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-27 07:35:33","doi":"10.21203/rs.3.rs-8208943/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":"ed81d30f-bcb1-4766-8ad1-01209863f3ff","owner":[],"postedDate":"November 27th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-11-27T07:35:33+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-27 07:35:33","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8208943","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8208943","identity":"rs-8208943","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}