Adaptive Privacy-Preserving Split-Hierarchical Federated Learning for Resource-Constrained IoT Networks

Adaptive Privacy-Preserving Split-Hierarchical Federated Learning for Resource-Constrained IoT Networks | 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 Privacy-Preserving Split-Hierarchical Federated Learning for Resource-Constrained IoT Networks Yashraj Sakunde This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8472732/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 The proliferation of Internet-of-Things (IoT) devices necessitates efficient machine learning paradigms that address bandwidth constraints, privacy requirements, and computational heterogeneity. While hierarchical federated learning offers com- munication efficiency and split learning reduces computational burden on resource-constrained devices, existing approaches lack adaptive mechanisms for dynamic environments and formal privacy guarantees. We propose AP-SHFL (Adaptive Privacy- Preserving Split-Hierarchical Federated Learning), a novel three- tier architecture that jointly optimizes split point selection, hierarchical aggregation, and differential privacy mechanisms. Our approach employs Q-learning for per-client dynamic split point adaptation based on real-time loss and communication feed- back, while implementing staleness-adaptive differential privacy that calibrates noise injection according to model freshness in asynchronous settings. Experimental results on MNIST demon- strate 99.19% test accuracy, 40-60% communication reduction compared to FedAvg baseline, rapid convergence (>98.5% in <10 rounds), and adaptive split point evolution from an average of 1.10 to 2.75 across clients, showcasing effective per-client optimization. Ablation studies confirm the contribution of each component. Our framework achieves state-of-the-art results, outperforming HSFL (98.1% accuracy) while maintaining formal differential privacy guarantees. Artificial Intelligence and Machine Learning Systems and Networking Federated Learning Split Learning Differential Privacy IoT Edge Computing Hierarchical Aggregation Q Learning Adaptive Optimization 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-8472732","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":566807425,"identity":"31995442-643b-4ad5-a2ac-44300c722597","order_by":0,"name":"Yashraj Sakunde","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAklEQVRIiWNgGAWjYHACNgjmYQBhGyDJ2HiAFC1pIC0NxGhhgGk5DGbj1WJw/PizxxU1fPb8PWfMHrypOG+3tv0w0JYam2icWs7kmBueOcaWOONsj7nhnDO3k7edSQRqOZaW24BLy4EcNskGNrYEhvM8ZtK8bbeTzQ4AtTA2HMat5fzzZ5IN/9js5cFa/p1LNjv/kICWGwlmko1tbIwbzvYAtTQcsDO7QcAWyRtvgFr62BI3njlWJjnnWHKC2Q2gLQl4/MJ3Ph3osG/H7OXOJG+TeFNjZ292Pv3hgw81Nji1KBwAU8fgAolglQk4lIOAPMSsGriAPR7Fo2AUjIJRMEIBAEKXZVHIjFt1AAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0002-8459-0038","institution":"Manipal Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Yashraj","middleName":"","lastName":"Sakunde","suffix":""}],"badges":[],"createdAt":"2025-12-29 11:52:50","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-8472732/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8472732/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":99792917,"identity":"56b6dae9-d34c-4537-9c2e-457592113f97","added_by":"auto","created_at":"2026-01-08 13:28:42","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":571314,"visible":true,"origin":"","legend":"","description":"","filename":"APSHFLAdaptivePrivacyPreservingSplitHFL.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8472732/v1_covered_ef23bbf1-647c-4875-8439-472500722392.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eAdaptive Privacy-Preserving Split-Hierarchical Federated Learning for Resource-Constrained IoT Networks\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Manipal University","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":"Federated Learning, Split Learning, Differential Privacy, IoT, Edge Computing, Hierarchical Aggregation, Q Learning, Adaptive Optimization","lastPublishedDoi":"10.21203/rs.3.rs-8472732/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8472732/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe proliferation of Internet-of-Things (IoT) devices necessitates efficient machine learning paradigms that address bandwidth constraints, privacy requirements, and computational heterogeneity. While hierarchical federated learning offers com- munication efficiency and split learning reduces computational burden on resource-constrained devices, existing approaches lack adaptive mechanisms for dynamic environments and formal privacy guarantees. We propose AP-SHFL (Adaptive Privacy- Preserving Split-Hierarchical Federated Learning), a novel three- tier architecture that jointly optimizes split point selection, hierarchical aggregation, and differential privacy mechanisms. Our approach employs Q-learning for per-client dynamic split point adaptation based on real-time loss and communication feed- back, while implementing staleness-adaptive differential privacy that calibrates noise injection according to model freshness in asynchronous settings. Experimental results on MNIST demon- strate 99.19% test accuracy, 40-60% communication reduction compared to FedAvg baseline, rapid convergence (\u0026gt;98.5% in \u0026lt;10 rounds), and adaptive split point evolution from an average of 1.10 to 2.75 across clients, showcasing effective per-client optimization. Ablation studies confirm the contribution of each component. Our framework achieves state-of-the-art results, outperforming HSFL (98.1% accuracy) while maintaining formal differential privacy guarantees.\u003c/p\u003e","manuscriptTitle":"Adaptive Privacy-Preserving Split-Hierarchical Federated Learning for Resource-Constrained IoT Networks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-06 03:17:16","doi":"10.21203/rs.3.rs-8472732/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":"7e8139a6-3613-4cba-b4f3-b124a9ebbd7c","owner":[],"postedDate":"January 6th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":60328944,"name":"Artificial Intelligence and Machine Learning"},{"id":60328945,"name":"Systems and Networking"}],"tags":[],"updatedAt":"2026-01-06T03:17:16+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-06 03:17:16","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8472732","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8472732","identity":"rs-8472732","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}