Kolmogorov-Arnold Networks: A Critical Assessment of Claims, Performance, and Practical Viability

Kolmogorov-Arnold Networks: A Critical Assessment of Claims, Performance, and Practical Viability | 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 Kolmogorov-Arnold Networks: A Critical Assessment of Claims, Performance, and Practical Viability Yuntian Hou, Tianrui Ji, Di Zhang, Angelos Stefanidis This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7063327/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 Kolmogorov-Arnold Networks (KANs) have gained significant attention as an alternative to traditional multilayer perceptrons, with proponents claiming superior interpretability and performance through learnable univariate activation functions. However, recent systematic evaluations reveal substantial discrepancies between theoretical claims and empirical evidence. This critical assessment examines KANs' actual performance across diverse domains using fair comparison methodologies that control for parameters and computational costs. Our analysis demonstrates that KANs outperform MLPs only in symbolic regression tasks, while consistently underperforming in machine learning, computer vision, and natural language processing benchmarks. The claimed advantages largely stem from B-spline activation functions rather than architectural innovations, and computational overhead (1.36-100× slower) severely limits practical deployment. Furthermore, theoretical claims about breaking the "curse of dimensionality" lack rigorous mathematical foundation. We systematically identify the conditions under which KANs provide value versus traditional approaches, establish evaluation standards for future research, and propose a priority-based roadmap for addressing fundamental limitations. This work provides researchers and practitioners with evidence-based guidance for the rational adoption of KANs while highlighting critical research gaps that must be addressed for broader applicability. Kolmogorov-Arnold Networks Neural Networks Machine Learning Deep Learning Interpretability Performance Evaluation 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-7063327","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":492614834,"identity":"75605967-5762-4afa-a2c4-e1ccdec24b66","order_by":0,"name":"Yuntian Hou","email":"","orcid":"","institution":"Xi’an Jiaotong-Liverpool University","correspondingAuthor":false,"prefix":"","firstName":"Yuntian","middleName":"","lastName":"Hou","suffix":""},{"id":492614835,"identity":"8bb54c3f-fce1-46ae-9318-a5a5b2badc9c","order_by":1,"name":"Tianrui Ji","email":"","orcid":"","institution":"Xi’an Jiaotong-Liverpool University","correspondingAuthor":false,"prefix":"","firstName":"Tianrui","middleName":"","lastName":"Ji","suffix":""},{"id":492614836,"identity":"2a71fff6-7e07-4341-803a-2dc0f9d1287e","order_by":2,"name":"Di Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8UlEQVRIie3RsWrDMBSF4WME9qLEq0MgeQUbQ6cSv8oVWjtkylSoQOCxs/sWhUJnF0G9hM4eOqRLuwYMGUPlJGSUPRaqf5AvQh9CGPD5/mAFQ9T1QwwQdv1UD5BMA3k/zBSEojEkrS/EDsFI0gByff+5emnpZydKLKYtBd3aRQxgqvdv+bqthbIkn7XE5pWbBJqHRt406kTEc0sh427CGD8amWucyMMYErJJaVZpdL6F0iGS6aBkk0dDiX1LRR9J9rT90nMXKWLTdPxgiri6o/1+c7ucNvKtcxHYv9GvQoGT/SbXncEKIKpHnfT5fL7/1y8KCVCcFYo4tAAAAABJRU5ErkJggg==","orcid":"","institution":"Xi’an Jiaotong-Liverpool University","correspondingAuthor":true,"prefix":"","firstName":"Di","middleName":"","lastName":"Zhang","suffix":""},{"id":492614837,"identity":"ff036eb3-9316-45c7-a9df-9019114c14e4","order_by":3,"name":"Angelos Stefanidis","email":"","orcid":"","institution":"Xi’an Jiaotong-Liverpool University","correspondingAuthor":false,"prefix":"","firstName":"Angelos","middleName":"","lastName":"Stefanidis","suffix":""}],"badges":[],"createdAt":"2025-07-07 08:53:34","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7063327/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7063327/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96916318,"identity":"e190c360-1ccb-45aa-8715-e71907455d11","added_by":"auto","created_at":"2025-11-27 14:08:28","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":844386,"visible":true,"origin":"","legend":"","description":"","filename":"ArticleTitleKAN.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7063327/v1_covered_6d55d5eb-0aea-43c6-ad90-76670a1d77d9.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Kolmogorov-Arnold Networks: A Critical Assessment of Claims, Performance, and Practical Viability","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":"Kolmogorov-Arnold Networks, Neural Networks, Machine Learning, Deep Learning, Interpretability, Performance Evaluation","lastPublishedDoi":"10.21203/rs.3.rs-7063327/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7063327/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eKolmogorov-Arnold Networks (KANs) have gained significant attention as an alternative to traditional multilayer perceptrons, with proponents claiming superior interpretability and performance through learnable univariate activation functions. However, recent systematic evaluations reveal substantial discrepancies between theoretical claims and empirical evidence. This critical assessment examines KANs' actual performance across diverse domains using fair comparison methodologies that control for parameters and computational costs. Our analysis demonstrates that KANs outperform MLPs only in symbolic regression tasks, while consistently underperforming in machine learning, computer vision, and natural language processing benchmarks. The claimed advantages largely stem from B-spline activation functions rather than architectural innovations, and computational overhead (1.36-100\u0026times; slower) severely limits practical deployment. Furthermore, theoretical claims about breaking the \"curse of dimensionality\" lack rigorous mathematical foundation. We systematically identify the conditions under which KANs provide value versus traditional approaches, establish evaluation standards for future research, and propose a priority-based roadmap for addressing fundamental limitations. This work provides researchers and practitioners with evidence-based guidance for the rational adoption of KANs while highlighting critical research gaps that must be addressed for broader applicability.\u003c/p\u003e","manuscriptTitle":"Kolmogorov-Arnold Networks: A Critical Assessment of Claims, Performance, and Practical Viability","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-30 19:40:46","doi":"10.21203/rs.3.rs-7063327/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":"ed57cb49-1e80-41ad-a1e5-40b4946620b9","owner":[],"postedDate":"July 30th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-11-26T03:38:59+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-30 19:40:46","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7063327","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7063327","identity":"rs-7063327","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}