Deep Transferable Label Propagation with Prototypical Augmentation

Deep Transferable Label Propagation with Prototypical Augmentation | 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 Article Deep Transferable Label Propagation with Prototypical Augmentation Yufang Dan, Li Zhu, Di Zhou This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9070462/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract Domain adaptation (DA) seeks to utilize ample labeled data from a source domain to boost the generalization capability of models on an unlabeled target domain with divergent data distributions. Label Propagation (LP) has emerged as an efficient semi-supervised learning paradigm for DA, transferring labels between the source and target domains based on a similarity graph. Nevertheless, existing LP-based DA methods still face significant challenges: 1) Semantic insufficiency in the source training domain impairs the performance of classes with sparse structures, particularly minority classes; 2) Generated pseudo-labels exhibit low reliability due to ambiguous feature distributions; 3) The two-phase architecture decouples domain-invariant feature learning from label propagation, thus failing to achieve mutual enhancement between these two processes for DA tasks; 4) Sample-level graph construction incurs prohibitive computational costs and poor scalability when handling large-scale datasets. To address these issues, we propose a novel DA strategy, Deep Transferable Label Propagation (DTLP), that integrates prototypical augmentation techniques. Specifically, DTLP embeds three core modules into a unified end-to-end system: 1) Prototype-guided feature augmentation, termed Prototypical Augmentation (ProAug), which enriches the semantic content of the source domain by interpolating samples with class prototypes to mitigate semantic deficiency; 2) Prototype graph-based label propagation, which constructs a class-level prototypical graph rather than a sample-level one to reduce computational complexity and alleviate class imbalance; 3) Domain alignment via prototypical contrastive learning, which facilitates dynamic mutual optimization between domain-invariant feature extraction and robust label propagation while narrowing domain discrepancy. Comprehensive experiments on various benchmark datasets demonstrate that the proposed DTLP outperforms state-of-the-art LP-based DA methods, validating its effectiveness and generalizability. Biological sciences/Computational biology and bioinformatics Physical sciences/Mathematics and computing domain adaptation prototypical augmentation label propagation prototypical graph Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 19 Apr, 2026 Reviews received at journal 14 Apr, 2026 Reviews received at journal 13 Apr, 2026 Reviewers agreed at journal 12 Apr, 2026 Reviewers agreed at journal 08 Apr, 2026 Reviewers agreed at journal 07 Apr, 2026 Reviewers invited by journal 07 Apr, 2026 Editor assigned by journal 07 Apr, 2026 Editor invited by journal 16 Mar, 2026 Submission checks completed at journal 13 Mar, 2026 First submitted to journal 12 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-9070462","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":622857529,"identity":"f1929bc0-9535-45e5-a475-9599c30015fa","order_by":0,"name":"Yufang Dan","email":"","orcid":"","institution":"Zhejiang Institute of Economics and Trade","correspondingAuthor":false,"prefix":"","firstName":"Yufang","middleName":"","lastName":"Dan","suffix":""},{"id":622857530,"identity":"5fc8547d-d3e3-4e95-8546-0135395a4ca3","order_by":1,"name":"Li Zhu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6klEQVRIiWNgGAWjYBACfmbGxgcJFf/kGCTAfGbCWiTbm5sNPpw5YAzUwthAlBaDM8fbJGe2HUhsIFoLw43ENmketjvp26V7jz9gqLBObGA/ewCvDsYZic3WPDzPcnfOOZfYwHAmPbGBJy8BrxZmicTG2zwSzLkbbuQYNjC2HQa6kMcArxY2icQGaR4D5nQDsJZ/RGjh4TnYJDkj4XACREsDEVok2BuBgXwgzXDDnXOJMxKOpRu38eTg12J/mP3hg8R/NvIGt3sPfPhQYy3bz34GvxZkNzIwJIB8R6x6iJZRMApGwSgYBdgAAJc8TOnHu2w9AAAAAElFTkSuQmCC","orcid":"","institution":"Guangzhou Maritime University","correspondingAuthor":true,"prefix":"","firstName":"Li","middleName":"","lastName":"Zhu","suffix":""},{"id":622857531,"identity":"607d1646-581e-47e0-bccf-e8d17df72e01","order_by":2,"name":"Di Zhou","email":"","orcid":"","institution":"Sichuan University of Arts and Science","correspondingAuthor":false,"prefix":"","firstName":"Di","middleName":"","lastName":"Zhou","suffix":""}],"badges":[],"createdAt":"2026-03-09 08:38:36","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9070462/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9070462/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106952190,"identity":"ef158cd8-23fa-47d6-bd57-ce563a404999","added_by":"auto","created_at":"2026-04-15 07:43:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2034749,"visible":true,"origin":"","legend":"","description":"","filename":"DeepTransferableLabelPropagationonPrototypicalGraphStatisticsandcomputing.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9070462/v1_covered_134b5e9a-f461-4ceb-a893-8e3c1b0bfc24.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Deep Transferable Label Propagation with Prototypical Augmentation","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"domain adaptation, prototypical augmentation, label propagation, prototypical graph","lastPublishedDoi":"10.21203/rs.3.rs-9070462/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9070462/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Domain adaptation (DA) seeks to utilize ample labeled data from a source domain to boost the generalization capability of models on an unlabeled target domain with divergent data distributions. Label Propagation (LP) has emerged as an efficient semi-supervised learning paradigm for DA, transferring labels between the source and target domains based on a similarity graph. Nevertheless, existing LP-based DA methods still face significant challenges: 1) Semantic insufficiency in the source training domain impairs the performance of classes with sparse structures, particularly minority classes; 2) Generated pseudo-labels exhibit low reliability due to ambiguous feature distributions; 3) The two-phase architecture decouples domain-invariant feature learning from label propagation, thus failing to achieve mutual enhancement between these two processes for DA tasks; 4) Sample-level graph construction incurs prohibitive computational costs and poor scalability when handling large-scale datasets. To address these issues, we propose a novel DA strategy, Deep Transferable Label Propagation (DTLP), that integrates prototypical augmentation techniques. Specifically, DTLP embeds three core modules into a unified end-to-end system: 1) Prototype-guided feature augmentation, termed Prototypical Augmentation (ProAug), which enriches the semantic content of the source domain by interpolating samples with class prototypes to mitigate semantic deficiency; 2) Prototype graph-based label propagation, which constructs a class-level prototypical graph rather than a sample-level one to reduce computational complexity and alleviate class imbalance; 3) Domain alignment via prototypical contrastive learning, which facilitates dynamic mutual optimization between domain-invariant feature extraction and robust label propagation while narrowing domain discrepancy. Comprehensive experiments on various benchmark datasets demonstrate that the proposed DTLP outperforms state-of-the-art LP-based DA methods, validating its effectiveness and generalizability.","manuscriptTitle":"Deep Transferable Label Propagation with Prototypical Augmentation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-15 07:41:40","doi":"10.21203/rs.3.rs-9070462/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-20T03:03:07+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-14T09:18:12+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-13T12:32:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"153294871547966330089302701445191630538","date":"2026-04-13T00:15:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"151127803450256212057442473054010396152","date":"2026-04-08T06:30:53+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"108349836684400870756585683715655394626","date":"2026-04-08T01:38:42+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-08T01:37:02+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-08T01:27:37+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-03-16T10:11:53+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-13T11:50:29+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-03-12T14:24:35+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"1614e41b-d590-4ead-a531-6ec114a141ff","owner":[],"postedDate":"April 15th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":66281385,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":66281386,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-05-13T08:55:50+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-15 07:41:40","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9070462","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9070462","identity":"rs-9070462","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}