A Novel Neural Network-Based Federated Learning System for Imbalanced and Non-IID Data

A Novel Neural Network-Based Federated Learning System for Imbalanced and Non-IID Data | 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 Novel Neural Network-Based Federated Learning System for Imbalanced and Non-IID Data Mahfuzur Rahman Chowdhury, Muhammad Ibrahim, Mridha Md Nafis Fuad This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7850701/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 With the growth of machine learning techniques, the privacy of users’ data has become a major concern. Most of the machine learning algorithms rely heavily on large amounts of data which may be collected from various sources. Collecting these data yet maintaining privacy policies has become one of the most challenging tasks for the researchers. To combat this issue, researchers have introduced federated learning, where a prediction model is learned by ensuring the privacy of clients’ data. However, the prevalent federated learning algorithms possess an accuracy and efficiency trade-off, especially for non-IID data. In this research, a centralized, neural network-based federated learning system is proposed. The centralized algorithm incorporates micro-level parallel processing inspired by the traditional mini-batch algorithm where the clients’ devices and the server handle the forward and backward propagation respectively. A semi-centralized version of the proposed algorithm is also devised. This algorithm takes advantage of edge computing to minimize the load from the central server, where clients handle both the forward and backward propagation while sacrificing the overall train time to some extent. The proposed systems are evaluated on five well-known benchmark datasets and achieve satisfactory performance in a reasonable time across various data distribution settings as compared to some existing benchmark algorithms. Artificial Intelligence and Machine Learning Machine Learning Deep Learning Neural Network Federated Learning Data Privacy Data Distribution 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-7850701","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":528959202,"identity":"21f95b92-f44d-4f3e-bb05-5af1df4ae6bb","order_by":0,"name":"Mahfuzur Rahman Chowdhury","email":"","orcid":"","institution":"Department of Computer Science and Engineering, University of Dhaka, Bangladesh","correspondingAuthor":false,"prefix":"","firstName":"Mahfuzur","middleName":"Rahman","lastName":"Chowdhury","suffix":""},{"id":528959203,"identity":"bef065f9-270c-41f2-a29e-55954c8b8b1c","order_by":1,"name":"Muhammad Ibrahim","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1ElEQVRIiWNgGAWjYBACNgkGBmYGAwY7Nv7mAxJgIQkglxgtyXwSxxKI08IA1sLAwDiPIceAOC180r0PPxcUbGNmYzjz8TYPg508g3TzBvwOkzluLD3D4DYfG3PvZmsehmTDBpljBQT8ksYgzWNwG2jL2W3SPAzMCQwSOYS8n8b8G6iFsY0h5xlQSz1RWtikoVqADIbDRGiROcZmDdSSzCZxzNhyjsFxwzZCfpGf3cZ8m+fPbTv5/uaHN95UVMvzEwoxNAB0Ehsp6kfBKBgFo2AUYAcA8zg3XCHtGYEAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0003-3284-8535","institution":"Department of Computer Science and Engineering, University of Dhaka, Bangladesh","correspondingAuthor":true,"prefix":"","firstName":"Muhammad","middleName":"","lastName":"Ibrahim","suffix":""},{"id":528959204,"identity":"0a9ddb5b-1dc7-4228-bb81-7e09413ebb35","order_by":2,"name":"Mridha Md Nafis Fuad","email":"","orcid":"","institution":"Institute of Information Technology, University of Dhaka, Bangladesh","correspondingAuthor":false,"prefix":"","firstName":"Mridha","middleName":"Md Nafis","lastName":"F","suffix":"Md"}],"badges":[],"createdAt":"2025-10-13 15:39:06","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-7850701/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7850701/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93507543,"identity":"9d4eeb94-c1e5-48ef-98a7-ab8a22eef8f7","added_by":"auto","created_at":"2025-10-14 14:55:45","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1472152,"visible":true,"origin":"","legend":"","description":"","filename":"FederatedLearningPaperIbrahimSir.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7850701/v1_covered_972612cd-5aed-4293-b49f-73568cf270c5.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eA Novel Neural Network-Based Federated Learning System for Imbalanced and Non-IID Data\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"University of Dhaka","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, Deep Learning, Neural Network, Federated Learning, Data Privacy, Data Distribution","lastPublishedDoi":"10.21203/rs.3.rs-7850701/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7850701/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eWith the growth of machine learning techniques, the privacy of users’ data has become a major concern. Most of the machine learning algorithms rely heavily on large amounts of data which may be collected from various sources. Collecting these data yet maintaining privacy policies has become one of the most challenging tasks for the researchers. To combat this issue, researchers have introduced federated learning, where a prediction model is learned by ensuring the privacy of clients’ data. However, the prevalent federated learning algorithms possess an accuracy and efficiency trade-off, especially for non-IID data. In this research, a centralized, neural network-based federated learning system is proposed. The centralized algorithm incorporates micro-level parallel processing inspired by the traditional mini-batch algorithm where the clients’ devices and the server handle the forward and backward propagation respectively. A semi-centralized version of the proposed algorithm is also devised. This algorithm takes advantage of edge computing to minimize the load from the central server, where clients handle both the forward and backward propagation while sacrificing the overall train time to some extent. The proposed systems are evaluated on five well-known benchmark datasets and achieve satisfactory performance in a reasonable time across various data distribution settings as compared to some existing benchmark algorithms.\u003c/p\u003e","manuscriptTitle":"A Novel Neural Network-Based Federated Learning System for Imbalanced and Non-IID Data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-14 14:47:36","doi":"10.21203/rs.3.rs-7850701/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":"e944d9c6-ceef-4b6d-8d76-84a91434c85b","owner":[],"postedDate":"October 14th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":56220556,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-10-14T14:47:36+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-14 14:47:36","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7850701","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7850701","identity":"rs-7850701","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}