FedAEF: Optimizing federated learning with mining and enhancing local data features

FedAEF: Optimizing federated learning with mining and enhancing local data features | 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 FedAEF: Optimizing federated learning with mining and enhancing local data features Yan Zeng, Chengchuang Huang, Siyuan Teng, Meiting Xue, Yukun Shi, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4768253/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract Federated learning is a distributed machine learning method for training models with data localization. However, data generated by local devices is often heterogeneous(non-independent and identically distributed, Non-IID), as it is influenced by time, geographical location, and sampling bias, which can lead to suboptimal performance and slower convergence of models. Most methods mitigate this issue by adjusting the optimization direction on the local device or leveraging shared datasets. However, they still can't work well for Non-IID data, due to the insufficient utilization of local high-quality data. For these problems, we propose an optimizing method, FedAEF. It trains autoencoders on local devices to extract local data features, and the server aggregates these features and generates independent and identically distributed (IID) data to fine-tune the global model. Experiments show that, compared to FedAVG, FedProx, and SCAFFOLD, FedAEF improves the accuracy by 2.5%, and the convergence performance of the model is improved by 55.9%. Federated learning model aggregation fine-tuned Non-IID Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 11 Aug, 2024 Reviewers invited by journal 11 Aug, 2024 Editor assigned by journal 23 Jul, 2024 Submission checks completed at journal 22 Jul, 2024 First submitted to journal 19 Jul, 2024 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-4768253","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":339590693,"identity":"bb1420a7-4d5a-44ce-9afc-c83aad0fa294","order_by":0,"name":"Yan Zeng","email":"","orcid":"","institution":"Hangzhou Dianzi University","correspondingAuthor":false,"prefix":"","firstName":"Yan","middleName":"","lastName":"Zeng","suffix":""},{"id":339590694,"identity":"27e4ef14-0d10-4d08-9f99-f6cea28018ff","order_by":1,"name":"Chengchuang Huang","email":"","orcid":"","institution":"Hangzhou Dianzi University","correspondingAuthor":false,"prefix":"","firstName":"Chengchuang","middleName":"","lastName":"Huang","suffix":""},{"id":339590695,"identity":"41872e18-b62b-458b-8b13-8adff5d26413","order_by":2,"name":"Siyuan Teng","email":"","orcid":"","institution":"Hangzhou Dianzi University","correspondingAuthor":false,"prefix":"","firstName":"Siyuan","middleName":"","lastName":"Teng","suffix":""},{"id":339590696,"identity":"48d0df3d-0b56-4234-ad52-2534a2d88c6d","order_by":3,"name":"Meiting Xue","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAsUlEQVRIiWNgGAWjYPACmwSGA0CKhwQtaaRrOUyCFt0Zucckfu44n8d3I4Hxwds2BnlzQlrMbuSlSfaeuV0seSOB2XBuG4PhzgaCWnLMJHjbbiduuJHAJs3bxpBgcIAILZJ/286BtLD/JloL0PADYFuYidNy5o2xtWxbcuLMMw+bJeeckzDcQFDL8RzDm2/b7BL7jicf/PCmzEaeoC1IgLEBSEgQr34UjIJRMApGAW4AAN7SQ6aEI1K8AAAAAElFTkSuQmCC","orcid":"","institution":"Hangzhou Dianzi University","correspondingAuthor":true,"prefix":"","firstName":"Meiting","middleName":"","lastName":"Xue","suffix":""},{"id":339590697,"identity":"908924b6-2afc-413b-b85f-333c32947e8f","order_by":4,"name":"Yukun Shi","email":"","orcid":"","institution":"Hangzhou Dianzi University","correspondingAuthor":false,"prefix":"","firstName":"Yukun","middleName":"","lastName":"Shi","suffix":""},{"id":339590698,"identity":"8aff0f06-db2e-482c-a06c-47c509eb233b","order_by":5,"name":"Jilin Zhang","email":"","orcid":"","institution":"Hangzhou Dianzi University","correspondingAuthor":false,"prefix":"","firstName":"Jilin","middleName":"","lastName":"Zhang","suffix":""},{"id":339590699,"identity":"6f5c9af7-e339-4dc2-9691-25426917f9ab","order_by":6,"name":"Jian Wan","email":"","orcid":"","institution":"Hangzhou Dianzi University","correspondingAuthor":false,"prefix":"","firstName":"Jian","middleName":"","lastName":"Wan","suffix":""},{"id":339590700,"identity":"82e6363a-e826-4ec0-9128-e11a2d041bc3","order_by":7,"name":"Gangyong Jia","email":"","orcid":"","institution":"Hangzhou Dianzi University","correspondingAuthor":false,"prefix":"","firstName":"Gangyong","middleName":"","lastName":"Jia","suffix":""}],"badges":[],"createdAt":"2024-07-19 14:27:35","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4768253/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4768253/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":62579017,"identity":"9f09bc12-19ab-4bdb-99af-2517696c2089","added_by":"auto","created_at":"2024-08-16 05:47:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":804984,"visible":true,"origin":"","legend":"","description":"","filename":"FedAEF22.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4768253/v1_covered_a5e9acbc-6a93-49d0-a66a-522ddaa8c441.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"FedAEF: Optimizing federated learning with mining and enhancing local data features","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"cluster-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Cluster Computing](https://www.springer.com/journal/10586)","snPcode":"10586","submissionUrl":"https://submission.nature.com/new-submission/10586/3","title":"Cluster Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Federated learning, model aggregation, fine-tuned, Non-IID","lastPublishedDoi":"10.21203/rs.3.rs-4768253/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4768253/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eFederated learning is a distributed machine learning method for training models with data localization. However, data generated by local devices is often heterogeneous(non-independent and identically distributed, Non-IID), as it is influenced by time, geographical location, and sampling bias, which can lead to suboptimal performance and slower convergence of models. Most methods mitigate this issue by adjusting the optimization direction on the local device or leveraging shared datasets. However, they still can't work well for Non-IID data, due to the insufficient utilization of local high-quality data. For these problems, we propose an optimizing method, FedAEF. It trains autoencoders on local devices to extract local data features, and the server aggregates these features and generates independent and identically distributed (IID) data to fine-tune the global model. Experiments show that, compared to FedAVG, FedProx, and SCAFFOLD, FedAEF improves the accuracy by 2.5%, and the convergence performance of the model is improved by 55.9%.\u003c/p\u003e","manuscriptTitle":"FedAEF: Optimizing federated learning with mining and enhancing local data features","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-16 05:39:37","doi":"10.21203/rs.3.rs-4768253/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"92878404039773583853224170120589915761","date":"2024-08-11T14:49:21+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-08-11T08:23:51+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-07-23T05:58:43+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-07-22T13:33:51+00:00","index":"","fulltext":""},{"type":"submitted","content":"Cluster Computing","date":"2024-07-19T14:26:14+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"cluster-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Cluster Computing](https://www.springer.com/journal/10586)","snPcode":"10586","submissionUrl":"https://submission.nature.com/new-submission/10586/3","title":"Cluster Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"afec2a03-f42c-4425-8ce7-6403b4853ac2","owner":[],"postedDate":"August 16th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-03-02T12:53:10+00:00","versionOfRecord":[],"versionCreatedAt":"2024-08-16 05:39:37","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4768253","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4768253","identity":"rs-4768253","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}