Towards Interpretable Trademark Infringement Prediction via Causal Representation Learning

Towards Interpretable Trademark Infringement Prediction via Causal Representation Learning | 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 Towards Interpretable Trademark Infringement Prediction via Causal Representation Learning Wei Zhou, Xingyu Wu, Guangyun Tan, Haotian Zhang, Linrui Xu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9186075/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 Trademark infringement prediction requires reliable similarity assessment to support consistent and explainable legal decisions. However, existing approaches predominantly rely on correlational feature learning, making them vulnerable to spurious patterns and limiting their interpretability—issues that are particularly critical in legal contexts. In this paper, we reformulate trademark similarity assessment through causal representation learning. This is challenging due to the highly entangled nature of trademark data and the absence of explicit causal supervision, which makes it difficult to identify stable and semantically meaningful factors. To address this, we propose a causally-informed generative framework that integrates a structural causal model with disentangled representation learning, enabling the joint enforcement of factor independence and intervention invariance. Our approach supports interpretable reasoning via latent-level interventions and counterfactual analysis. Experiments on both public and real-world datasets demonstrate that the proposed method consistently outperforms strong baselines while achieving improved robustness and interpretability. Causal Representation Learning Trademark Infringement Prediction Disentangled Representation Structural Causal Model Explainable AI 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-9186075","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":630400315,"identity":"cc8b5729-108c-412c-b90a-c5bd39234de6","order_by":0,"name":"Wei Zhou","email":"","orcid":"","institution":"China University of Political Science and Law","correspondingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"Zhou","suffix":""},{"id":630400316,"identity":"64c16909-69eb-440d-9d2d-051ccecc5b39","order_by":1,"name":"Xingyu Wu","email":"","orcid":"","institution":"The Hong Kong Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Xingyu","middleName":"","lastName":"Wu","suffix":""},{"id":630400317,"identity":"8a4379f7-33c9-470d-8718-9f62db9aa76b","order_by":2,"name":"Guangyun Tan","email":"","orcid":"","institution":"Hangzhou DIMeta Technology Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"Guangyun","middleName":"","lastName":"Tan","suffix":""},{"id":630400318,"identity":"7342dfba-6a14-4af7-8660-b4d66b41c68d","order_by":3,"name":"Haotian Zhang","email":"","orcid":"","institution":"China University of Political Science and Law","correspondingAuthor":false,"prefix":"","firstName":"Haotian","middleName":"","lastName":"Zhang","suffix":""},{"id":630400319,"identity":"56c3c65e-db6d-4600-a350-4d8d96db263e","order_by":4,"name":"Linrui Xu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/ElEQVRIie3Rv0rEMBzA8V8p1OXHdU2JnK/wKwUXC75KglCXGzq6mVLQ5R4g4kvcJm4pGVwKrhUXD0FX4UZFzHUTIe3okC+EEsiH/ClAKPQPS9OmeflAhumBctPaDTNBMm3bXB+Wy2y9X0ozCJnzK45lVZAWMwmYTjFcWbnJXt94TbBcDCLa1R4RtY0i1lt5x6tjrgmKbBAx1x4SQ6dEvrby/naVcCSQm0EkMXpIAlIZ+e0O9tSP5HKSIMhGGXTXH3AkgqYIY10bKdw/clWcaGL5Tb9tuY+cPl6/f36Nv9Jun+uL8mjxcNbtfORXsdvVfSI1F4wkFAqFQn/7AUbWTNVU780RAAAAAElFTkSuQmCC","orcid":"","institution":"China University of Political Science and Law","correspondingAuthor":true,"prefix":"","firstName":"Linrui","middleName":"","lastName":"Xu","suffix":""}],"badges":[],"createdAt":"2026-03-21 13:25:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9186075/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9186075/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108182594,"identity":"82a7ef74-5645-4ab8-ad44-a7a821dae94a","added_by":"auto","created_at":"2026-04-30 08:59:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1043939,"visible":true,"origin":"","legend":"","description":"","filename":"anonymised.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9186075/v1_covered_948584b2-7bc4-49c2-a564-f8a1f6a71a7d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Towards Interpretable Trademark Infringement Prediction via Causal Representation Learning","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":"Causal Representation Learning, Trademark Infringement Prediction, Disentangled Representation, Structural Causal Model, Explainable AI","lastPublishedDoi":"10.21203/rs.3.rs-9186075/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9186075/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTrademark infringement prediction requires reliable similarity assessment to support consistent and explainable legal decisions. However, existing approaches predominantly rely on correlational feature learning, making them vulnerable to spurious patterns and limiting their interpretability\u0026mdash;issues that are particularly critical in legal contexts. In this paper, we reformulate trademark similarity assessment through causal representation learning. This is challenging due to the highly entangled nature of trademark data and the absence of explicit causal supervision, which makes it difficult to identify stable and semantically meaningful factors. To address this, we propose a causally-informed generative framework that integrates a structural causal model with disentangled representation learning, enabling the joint enforcement of factor independence and intervention invariance. Our approach supports interpretable reasoning via latent-level interventions and counterfactual analysis. Experiments on both public and real-world datasets demonstrate that the proposed method consistently outperforms strong baselines while achieving improved robustness and interpretability.\u003c/p\u003e","manuscriptTitle":"Towards Interpretable Trademark Infringement Prediction via Causal Representation Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-30 04:40:35","doi":"10.21203/rs.3.rs-9186075/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":"92b0f852-0dcb-407c-8117-3fa2b35a0e5e","owner":[],"postedDate":"April 30th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-30T04:40:35+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-30 04:40:35","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9186075","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9186075","identity":"rs-9186075","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}