A practical evaluation of AutoML tools for binary, multiclass, and multilabel classification

A practical evaluation of AutoML tools for binary, multiclass, and multilabel classification | 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 A practical evaluation of AutoML tools for binary, multiclass, and multilabel classification Marcelo V. C. Aragão, Augusto G. Afonso, Rafaela C. Ferraz, Rairon G. Ferreira, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4172933/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 Choosing the right Automated Machine Learning (AutoML) tool is crucial for researchers of varying expertise to achieve optimal performance in diverse classification tasks. However, the abundance of AutoML frameworks with varying features makes selection challenging. This study addresses this gap by conducting a practical evaluation informed by a theoretical and bibliographical review and a feature-based comparison of twelve AutoML frameworks. The evaluation, conducted under time constraints, assessed accuracy and training efficiency across binary, multiclass, and multilabel (considering both native and label powerset representations) classification tasks on fifteen datasets. We acknowledge limitations, including dataset scope and default parameter usage, which may not capture the full potential of some frameworks. Our findings reveal no single ``perfect'' tool, as frameworks prioritize accuracy or speed. For time-sensitive binary/multiclass tasks, \claas, \autogluon, and \autokeras showed promise. In multilabel scenarios, \autosklearn offered higher accuracy, while \autokeras excelled in training speed. These results highlight the crucial trade-off between accuracy and speed, emphasizing the importance of considering both factors during tool selection for binary, multiclass, and multilabel classification problems. We made the code, experiment reproduction instructions, and outcomes publicly available on GitHub. Machine Learning Classification Hyperparameter Optimization Neural Architecture Search AutoML 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-4172933","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":287760749,"identity":"2603d623-b739-444f-aa02-8887ac5ffb74","order_by":0,"name":"Marcelo V. C. Aragão","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA50lEQVRIie3OoQoCMRzH8R2DswysJwf6BMJfBofhxGcZJ7MYziLGma4MrHsSk2GyemI1GDyE5YsGg6dN0Dtthn3D+IV92BByuf629HFgrUt4DoGbyfOmzwpVDYK8rwmhlKAvSD/bF2UJMVtneRTG6ak3bq0Enm8/kyif0o4CzlTOF+EM7ECSncDK1hDNfUzAUEDJpiLGkwETmOgacrA+vj1I+xyFQzBj2SsayLF6BYHpQjChtBpMBl4TsbgjgXeDo2WFBJPInAmjaj/GvfK6jEl7nWh9vZlRlpndJa0h7/sZuFwul+u1O9MjUaJNmC5BAAAAAElFTkSuQmCC","orcid":"","institution":"National Institute of Telecommunications","correspondingAuthor":true,"prefix":"","firstName":"Marcelo","middleName":"V. C.","lastName":"Aragão","suffix":""},{"id":287760750,"identity":"6f574bc9-f144-486e-9cf0-ddd3152b5a64","order_by":1,"name":"Augusto G. Afonso","email":"","orcid":"","institution":"National Institute of Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Augusto","middleName":"G.","lastName":"Afonso","suffix":""},{"id":287760751,"identity":"f346b3fc-31bc-4aed-98d1-7463357aff38","order_by":2,"name":"Rafaela C. Ferraz","email":"","orcid":"","institution":"National Institute of Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Rafaela","middleName":"C.","lastName":"Ferraz","suffix":""},{"id":287760752,"identity":"193c4b53-ff6b-43e4-837e-43b86694e1b8","order_by":3,"name":"Rairon G. Ferreira","email":"","orcid":"","institution":"National Institute of Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Rairon","middleName":"G.","lastName":"Ferreira","suffix":""},{"id":287760753,"identity":"48318174-5b68-45e6-9f4a-834515ae1bb7","order_by":4,"name":"Sávio Leite","email":"","orcid":"","institution":"National Institute of Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Sávio","middleName":"","lastName":"Leite","suffix":""},{"id":287760754,"identity":"154710f5-3b21-403e-8e56-f6598ad2aecb","order_by":5,"name":"Felipe A. P. de Figueiredo","email":"","orcid":"","institution":"National Institute of Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Felipe","middleName":"A. P.","lastName":"de Figueiredo","suffix":""},{"id":287760755,"identity":"df744a9a-1a7a-4422-b3ab-eba6681c0edf","order_by":6,"name":"Samuel B. Mafra","email":"","orcid":"","institution":"National Institute of Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Samuel","middleName":"B.","lastName":"Mafra","suffix":""}],"badges":[],"createdAt":"2024-03-27 02:29:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4172933/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4172933/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":57273014,"identity":"72aae804-b570-4c7f-87c0-5e9f35c81a63","added_by":"auto","created_at":"2024-05-28 13:02:50","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4891356,"visible":true,"origin":"","legend":"","description":"","filename":"aragao2024automlcomparison.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4172933/v1_covered_392d55e2-346d-49da-b841-0e382bf0b8c6.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A practical evaluation of AutoML tools for binary, multiclass, and multilabel classification","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":"Machine Learning, Classification, Hyperparameter Optimization, Neural Architecture Search, AutoML","lastPublishedDoi":"10.21203/rs.3.rs-4172933/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4172933/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eChoosing the right Automated Machine Learning (AutoML) tool is crucial for researchers of varying expertise to achieve optimal performance in diverse classification tasks. However, the abundance of AutoML frameworks with varying features makes selection challenging. This study addresses this gap by conducting a practical evaluation informed by a theoretical and bibliographical review and a feature-based comparison of twelve AutoML frameworks. The evaluation, conducted under time constraints, assessed accuracy and training efficiency across binary, multiclass, and multilabel (considering both native and label powerset representations) classification tasks on fifteen datasets. We acknowledge limitations, including dataset scope and default parameter usage, which may not capture the full potential of some frameworks. Our findings reveal no single ``perfect'' tool, as frameworks prioritize accuracy or speed. For time-sensitive binary/multiclass tasks, \\claas, \\autogluon, and \\autokeras showed promise. In multilabel scenarios, \\autosklearn offered higher accuracy, while \\autokeras excelled in training speed. These results highlight the crucial trade-off between accuracy and speed, emphasizing the importance of considering both factors during tool selection for binary, multiclass, and multilabel classification problems. We made the code, experiment reproduction instructions, and outcomes publicly available on GitHub.\u003c/p\u003e","manuscriptTitle":"A practical evaluation of AutoML tools for binary, multiclass, and multilabel classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-09 14:20:15","doi":"10.21203/rs.3.rs-4172933/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":"18426114-4041-4e0c-95e4-710a56df78c2","owner":[],"postedDate":"April 9th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-01-09T14:08:10+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-09 14:20:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4172933","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4172933","identity":"rs-4172933","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}