Adaptive Bottleneck Architecture Search for Resource-Constrained Continual Learning

Adaptive Bottleneck Architecture Search for Resource-Constrained Continual 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 Adaptive Bottleneck Architecture Search for Resource-Constrained Continual Learning Weijun Liu, Haoming Chen, Leifang Zhan, Jiaxin Wu, Zhou Shen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8201329/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 In this paper, we propose an innovative framework for addressing the dual challenges of neural architecture selection and resource allocation in resource-constrained continual learning environments. We formulate the adaptive bottleneck architecture search (ABAS) as a mixed-integer optimization problem, allowing for the dynamic adaptation of neural architectures to evolving data streams while managing limited computational and memory resources. Our approach leverages Lagrangian relaxation techniques to effectively balance trade-offs between model accuracy, resource utilization, and knowledge retention. Comprehensive theoretical analysis and extensive empirical evaluations highlight the superiority of our method over existing continual learning strategies and neural architecture search techniques, demonstrating significant improvements in performance metrics such as accuracy, forgetting, and resource efficiency. By bridging the gap between architecture adaptability and learning efficiency, our work paves the way for more effective deployment of machine learning systems in real-world applications where resources are often constrained. Our research not only contributes novel solutions to the field of continual learning but also opens avenues for future explorations of adaptive learning systems in diverse contexts. optimization continual learning neural architecture search resource constraints mixedinteger programming bottleneck selection Full Text Additional Declarations The authors declare no competing interests. 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-8201329","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":550455861,"identity":"65dcfa85-2ad1-4090-90c8-bafab2078bfa","order_by":0,"name":"Weijun Liu","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Weijun","middleName":"","lastName":"Liu","suffix":""},{"id":550455862,"identity":"783bbb5d-6653-4712-b75d-ae91c9ed33ae","order_by":1,"name":"Haoming Chen","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Haoming","middleName":"","lastName":"Chen","suffix":""},{"id":550455863,"identity":"49cd2778-e3ef-4874-86cc-d5f5925f9ee0","order_by":2,"name":"Leifang Zhan","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Leifang","middleName":"","lastName":"Zhan","suffix":""},{"id":550455864,"identity":"ad576edb-861a-4de1-853a-63d84f57ca30","order_by":3,"name":"Jiaxin Wu","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Jiaxin","middleName":"","lastName":"Wu","suffix":""},{"id":550455865,"identity":"d9c13d39-a8b8-4d62-81fe-db29ac2dd644","order_by":4,"name":"Zhou Shen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFElEQVRIiWNgGAWjYDACCSBmbEASMGAH8QwsSNHCcwBESpCiRSIBJo4dyM9uPvbw5w6bxAbpw4c/fKi5J28u+fzqhh8FEgz87d0J2LQY3DmWbiB5Ji2xgS8tTXLGsWLDnbNzym72AB0mcebsBqxaJHLMJAzbDic28PCYMfOwJSQY3M5Ju8ED1GIgkYtVi/yM/G8SiWAt/J8///kH1HLzTNrNP3i0MNzIYZM4CLGFQZqxDajlBvux2/hsMbiRZibZ2JZm3MbDZibZ25dguOFMDtttGQMJHlx+kZ+R/EzyZ5uNbD8P8+MPP74lyBscP/7s5ps/NnL87b3YHQYDbAgmjwGYxKscDbA/IEX1KBgFo2AUDH8AAA8DYpsNUdNBAAAAAElFTkSuQmCC","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Zhou","middleName":"","lastName":"Shen","suffix":""}],"badges":[],"createdAt":"2025-11-25 09:22:55","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8201329/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8201329/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96915761,"identity":"0279a432-c55c-4128-8a53-ce4590c6fc62","added_by":"auto","created_at":"2025-11-27 14:07:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":231376,"visible":true,"origin":"","legend":"","description":"","filename":"paper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8201329/v1_covered_73c2d022-ffd6-4754-88f1-c0ff2055594e.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eAdaptive Bottleneck Architecture Search for Resource-Constrained Continual Learning\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"optimization, continual learning, neural architecture search, resource constraints, mixedinteger programming, bottleneck selection","lastPublishedDoi":"10.21203/rs.3.rs-8201329/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8201329/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn this paper, we propose an innovative framework for addressing the dual challenges of neural architecture selection and resource allocation in resource-constrained continual learning environments. We formulate the adaptive bottleneck architecture search (ABAS) as a mixed-integer optimization problem, allowing for the dynamic adaptation of neural architectures to evolving data streams while managing limited computational and memory resources. Our approach leverages Lagrangian relaxation techniques to effectively balance trade-offs between model accuracy, resource utilization, and knowledge retention. Comprehensive theoretical analysis and extensive empirical evaluations highlight the superiority of our method over existing continual learning strategies and neural architecture search techniques, demonstrating significant improvements in performance metrics such as accuracy, forgetting, and resource efficiency. By bridging the gap between architecture adaptability and learning efficiency, our work paves the way for more effective deployment of machine learning systems in real-world applications where resources are often constrained. Our research not only contributes novel solutions to the field of continual learning but also opens avenues for future explorations of adaptive learning systems in diverse contexts.\u003c/p\u003e","manuscriptTitle":"Adaptive Bottleneck Architecture Search for Resource-Constrained Continual Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-26 02:50:08","doi":"10.21203/rs.3.rs-8201329/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":"ed81d30f-bcb1-4766-8ad1-01209863f3ff","owner":[],"postedDate":"November 26th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-11-26T02:50:08+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-26 02:50:08","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8201329","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8201329","identity":"rs-8201329","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}