A privacy preserving federated clustering algorithm for data imbalance based on density peak clustering and Gaussian distribution simulation data

A privacy preserving federated clustering algorithm for data imbalance based on density peak clustering and Gaussian distribution simulation 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 privacy preserving federated clustering algorithm for data imbalance based on density peak clustering and Gaussian distribution simulation data Jun Wang, XiangHua Chen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6549947/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 9 You are reading this latest preprint version Abstract Federated clustering is an unsupervised learning method that has emerged in recent years in distributed data environments. It aims to discover knowledge from data provided by multiple clients while protecting data privacy by combining federated learning and clustering techniques. However, there are significant challenges in data heterogeneity and communication. This paper proposes a new federated learning clustering method, DPG-PFC, to address the data imbalance problem. The core of the method is to obtain statistical information of clusters (such as variance, mean, etc.) through local density peaks clustering, and use this information on the server to reconstruct a simulated dataset by Gaussian distribution for re-clustering. To enhance privacy protection, a differential privacy mechanism is adopted to add noise to local data, ensuring privacy security during operations. Experiments on the MNIST dataset validate the effectiveness of the method. This method uses local density clustering to resolve the inconsistency in the number of clusters caused by data imbalance. Additionally, the method requires only one communication round, which significantly improves communication efficiency. Clustering Privacy Preservation Federated Learning k-means Non-IID Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 16 Sep, 2025 Reviews received at journal 10 Jun, 2025 Reviews received at journal 10 Jun, 2025 Reviewers agreed at journal 07 Jun, 2025 Reviewers agreed at journal 04 Jun, 2025 Reviewers invited by journal 04 Jun, 2025 Editor assigned by journal 01 May, 2025 Submission checks completed at journal 30 Apr, 2025 First submitted to journal 28 Apr, 2025 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-6549947","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":466326083,"identity":"b8f210c6-9d73-4df4-8d3f-f1fa3bc6ae42","order_by":0,"name":"Jun Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAElEQVRIiWNgGAWjYLACCQYGHnn25oMPoHwDorTIGfYcS4YpJUILEBgz3MgxkyBKi8Hxs4dfWLbdSWxsSDCrLmyzk2dgb94mwVBzB7eWM3lpFpJtzxLbGQ6k3Z7ZlmzYwHOsTILh2DOcWswO5JgZSLYdTmxsbDh2m7eNmbFBAuhCxobDuLWcfwPR0nCYsa2Yt63evkH+DQEtN3KMHwC1GDMcY2Zj5gXpleDBr8X+xhszBolzh4GBzMYszXPueHIbT1qxRcIx3Fok+3OMP0uUHeaRl3//8TNPWbVtP/vhjTc+1ODWAgRs0hIoXBCRgE8DAwPzxw/4FYyCUTAKRsFIBwAs2VWuPFH8QwAAAABJRU5ErkJggg==","orcid":"","institution":"Nanjing University of Aeronautics and Astronautics","correspondingAuthor":true,"prefix":"","firstName":"Jun","middleName":"","lastName":"Wang","suffix":""},{"id":466326084,"identity":"fbd298a3-3c55-4e1f-961d-cd34da78e73a","order_by":1,"name":"XiangHua Chen","email":"","orcid":"","institution":"Nanjing University of Aeronautics and Astronautics","correspondingAuthor":false,"prefix":"","firstName":"XiangHua","middleName":"","lastName":"Chen","suffix":""}],"badges":[],"createdAt":"2025-04-28 17:23:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6549947/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6549947/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":84037997,"identity":"b0967c1c-8bcd-49c7-a1fd-4863343b5f6c","added_by":"auto","created_at":"2025-06-06 04:39:57","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":367888,"visible":true,"origin":"","legend":"","description":"","filename":"20250429AprivacypreservingfederatedclusteringalgorithmfordataimbalancebasedondensitypeakclusteringandGaussiandistributionsimulationdata2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6549947/v1_covered_34569f9d-559a-47b5-a1ee-69f51871fedc.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A privacy preserving federated clustering algorithm for data imbalance based on density peak clustering and Gaussian distribution simulation data","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":"Clustering, Privacy Preservation, Federated Learning, k-means, Non-IID","lastPublishedDoi":"10.21203/rs.3.rs-6549947/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6549947/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eFederated clustering is an unsupervised learning method that has emerged in recent years in distributed data environments. It aims to discover knowledge from data provided by multiple clients while protecting data privacy by combining federated learning and clustering techniques. However, there are significant challenges in data heterogeneity and communication. This paper proposes a new federated learning clustering method, DPG-PFC, to address the data imbalance problem. The core of the method is to obtain statistical information of clusters (such as variance, mean, etc.) through local density peaks clustering, and use this information on the server to reconstruct a simulated dataset by Gaussian distribution for re-clustering. To enhance privacy protection, a differential privacy mechanism is adopted to add noise to local data, ensuring privacy security during operations. Experiments on the MNIST dataset validate the effectiveness of the method. This method uses local density clustering to resolve the inconsistency in the number of clusters caused by data imbalance. Additionally, the method requires only one communication round, which significantly improves communication efficiency.\u003c/p\u003e","manuscriptTitle":"A privacy preserving federated clustering algorithm for data imbalance based on density peak clustering and Gaussian distribution simulation data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-06 04:23:48","doi":"10.21203/rs.3.rs-6549947/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-16T19:37:14+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-10T16:07:26+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-10T15:07:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"51499881363380423667335209798557968643","date":"2025-06-07T05:04:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"62478092894351736699626227010754638464","date":"2025-06-04T08:59:09+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-04T07:17:00+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-01T22:28:04+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-30T14:00:47+00:00","index":"","fulltext":""},{"type":"submitted","content":"Cluster Computing","date":"2025-04-28T17:14:17+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":"f4d98b6b-8969-4d02-b995-cd8644e91757","owner":[],"postedDate":"June 6th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-02-04T23:08:34+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-06 04:23:48","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6549947","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6549947","identity":"rs-6549947","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}