DCMatchBoosted - Improving Deep Clustering by Architecture Recommendation

DCMatchBoosted - Improving Deep Clustering by Architecture Recommendation | 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 DCMatchBoosted - Improving Deep Clustering by Architecture Recommendation Mamdouh Aljoud, Gabriel Marques Tavares, Collin Leiber, Thomas Seidl This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7495778/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 08 Feb, 2026 Read the published version in International Journal of Data Science and Analytics → Version 1 posted 10 You are reading this latest preprint version Abstract Deep clustering algorithms such as Deep Embedded Clustering (DEC), Deep K-Means (DKM), and Deep Clustering Network (DCN) are highly sensitive to the architecture of the underlying neural network, heavily influencing clustering quality. Although Neural Architecture Search (NAS) methods aim at properly configuring deep neural networks, traditional NAS approaches are unsuitable in this context due to the absence of labels. We propose \textbf{DCMatchBoosted}, an extension of our previous framework (DCMatch), which leverages dataset characterization and a gradient boosting surrogate to recommend effective autoencoder architectures for deep clustering. Our method combines high-level semantic embeddings from CLIP with complementary statistical descriptors, extracted from a small subset of randomly sampled images, to build a compact representation of each dataset. These dataset features are paired with architecture metadata and used to train an XGBoost model that predicts clustering performance. In extensive experiments on 20 image datasets and three clustering algorithms (DEC, DKM, DCN), DCMatchBoosted consistently outperforms the default configurations, achieving statistically significant improvements in clustering accuracy on the majority of datasets. We make our code available here: https://github.com/mamdouhJ/DCMatch meta-learning deep clustering hyperparameter optimization Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 08 Feb, 2026 Read the published version in International Journal of Data Science and Analytics → Version 1 posted Editorial decision: Revision requested 01 Dec, 2025 Reviews received at journal 01 Dec, 2025 Reviewers agreed at journal 09 Nov, 2025 Reviews received at journal 09 Nov, 2025 Reviewers agreed at journal 09 Nov, 2025 Reviewers agreed at journal 14 Oct, 2025 Reviewers invited by journal 08 Oct, 2025 Editor assigned by journal 01 Sep, 2025 Submission checks completed at journal 01 Sep, 2025 First submitted to journal 30 Aug, 2025 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-7495778","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":531680865,"identity":"33c65538-7ae3-4f18-b629-8ac6a4d9f0f0","order_by":0,"name":"Mamdouh Aljoud","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA70lEQVRIie2RsQrCMBCGrwjtEnEtVOsTCBWhIIjPklBwdhJHQXDyATr4EN3E7SSDS2nXgovi6tDRoYOxEXE6HQXzTT8hH/9dAmAw/CIOcAB7ZCUq4zyA9uPQJZVGrUy0kgbAvlEUtqwVSOELpbWE84XN8s62hRbiFFgv5lZREoorIRqw7DjYxRwQ1WBhwRvDmKqRMPGaq6NICpVLrdgeI4yuVjKR5Phqsb2KUAKtoEiQvynUXH21S3+TRWoXsVCKy8L0vByuCcU/rMXpOhurF5OyxGrkh4doX9yoGmD8GawF6B+pA4WDHy4YDAbD33MH8l5QzCJZBXAAAAAASUVORK5CYII=","orcid":"","institution":"Ludwig-Maximilians-Universität München","correspondingAuthor":true,"prefix":"","firstName":"Mamdouh","middleName":"","lastName":"Aljoud","suffix":""},{"id":531680867,"identity":"80bf0fbe-dba9-47b1-979b-cbf866689625","order_by":1,"name":"Gabriel Marques Tavares","email":"","orcid":"","institution":"Ludwig-Maximilians-Universität München","correspondingAuthor":false,"prefix":"","firstName":"Gabriel","middleName":"Marques","lastName":"Tavares","suffix":""},{"id":531680869,"identity":"60c81531-26ae-46b9-af06-75c8dfcbf3b9","order_by":2,"name":"Collin Leiber","email":"","orcid":"","institution":"Aalto University","correspondingAuthor":false,"prefix":"","firstName":"Collin","middleName":"","lastName":"Leiber","suffix":""},{"id":531680870,"identity":"a3d082ba-94d3-415f-a71a-4337c69b4a8d","order_by":3,"name":"Thomas Seidl","email":"","orcid":"","institution":"Ludwig-Maximilians-Universität München","correspondingAuthor":false,"prefix":"","firstName":"Thomas","middleName":"","lastName":"Seidl","suffix":""}],"badges":[],"createdAt":"2025-08-30 14:08:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7495778/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7495778/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s41060-025-01009-1","type":"published","date":"2026-02-08T15:57:26+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":93983208,"identity":"1cc05d37-e3ca-4dbd-a09c-5d48099d9892","added_by":"auto","created_at":"2025-10-21 03:37:43","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5519,"visible":true,"origin":"","legend":"","description":"","filename":"7b646586459348ec96b5a53fc7589aea.json","url":"https://assets-eu.researchsquare.com/files/rs-7495778/v1/c1e63a8e1e87714ffce780d2.json"},{"id":102234072,"identity":"e65fdd60-e622-4641-881b-4c3729503563","added_by":"auto","created_at":"2026-02-09 16:05:38","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2366230,"visible":true,"origin":"","legend":"","description":"","filename":"DCMatchBoostedImprovingDeepClusteringbyArchitectureRecommendation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7495778/v1_covered_323a7e12-158d-4622-b057-8701d2a9b50e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"DCMatchBoosted - Improving Deep Clustering by Architecture Recommendation","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":"international-journal-of-data-science-and-analytics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jdsa","sideBox":"Learn more about [International Journal of Data Science and Analytics](http://link.springer.com/journal/41060)","snPcode":"41060","submissionUrl":"https://submission.nature.com/new-submission/41060/3","title":"International Journal of Data Science and Analytics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"meta-learning, deep clustering, hyperparameter optimization","lastPublishedDoi":"10.21203/rs.3.rs-7495778/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7495778/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Deep clustering algorithms such as Deep Embedded Clustering (DEC), Deep K-Means (DKM), and Deep Clustering Network (DCN) are highly sensitive to the architecture of the underlying neural network, heavily influencing clustering quality. Although Neural Architecture Search (NAS) methods aim at properly configuring deep neural networks, traditional NAS approaches are unsuitable in this context due to the absence of labels. We propose \\textbf{DCMatchBoosted}, an extension of our previous framework (DCMatch), which leverages dataset characterization and a gradient boosting surrogate to recommend effective autoencoder architectures for deep clustering. Our method combines high-level semantic embeddings from CLIP with complementary statistical descriptors, extracted from a small subset of randomly sampled images, to build a compact representation of each dataset. These dataset features are paired with architecture metadata and used to train an XGBoost model that predicts clustering performance. In extensive experiments on 20 image datasets and three clustering algorithms (DEC, DKM, DCN), DCMatchBoosted consistently outperforms the default configurations, achieving statistically significant improvements in clustering accuracy on the majority of datasets. We make our code available here: https://github.com/mamdouhJ/DCMatch","manuscriptTitle":"DCMatchBoosted - Improving Deep Clustering by Architecture Recommendation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-21 03:37:38","doi":"10.21203/rs.3.rs-7495778/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-01T22:25:17+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-01T05:43:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"90452354633929682418157596636220378165","date":"2025-11-09T23:17:08+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-09T23:01:15+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"331683634383516593241018011105174431687","date":"2025-11-09T22:12:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"70616243211147079672781046194590633653","date":"2025-10-14T07:20:58+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-08T16:29:45+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-01T08:03:12+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-01T07:44:04+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Data Science and Analytics","date":"2025-08-30T14:05:56+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-data-science-and-analytics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jdsa","sideBox":"Learn more about [International Journal of Data Science and Analytics](http://link.springer.com/journal/41060)","snPcode":"41060","submissionUrl":"https://submission.nature.com/new-submission/41060/3","title":"International Journal of Data Science and Analytics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"48796ebb-0f61-4e9d-83e1-1dac847b510d","owner":[],"postedDate":"October 21st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-02-09T16:01:58+00:00","versionOfRecord":{"articleIdentity":"rs-7495778","link":"https://doi.org/10.1007/s41060-025-01009-1","journal":{"identity":"international-journal-of-data-science-and-analytics","isVorOnly":false,"title":"International Journal of Data Science and Analytics"},"publishedOn":"2026-02-08 15:57:26","publishedOnDateReadable":"February 8th, 2026"},"versionCreatedAt":"2025-10-21 03:37:38","video":"","vorDoi":"10.1007/s41060-025-01009-1","vorDoiUrl":"https://doi.org/10.1007/s41060-025-01009-1","workflowStages":[]},"version":"v1","identity":"rs-7495778","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7495778","identity":"rs-7495778","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}