Incentivizing Inclusive Data Contributions in Personalized Federated Learning

Incentivizing Inclusive Data Contributions in Personalized Federated 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 Article Incentivizing Inclusive Data Contributions in Personalized Federated Learning Siheng Chen, Enpei Zhang, Jingyi Chai, Rui Ye, Yanfeng Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3927659/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 25 Aug, 2025 Read the published version in Nature Communications → Version 1 posted You are reading this latest preprint version Abstract While data plays a crucial role in training contemporary AI models, it is acknowledged that valuable public data will be exhausted in a few years, directing the world's attention towards the massive decentralized private data. However, the privacy-sensitive nature of raw data and lack of incentive mechanism prevent these valuable data from being fully exploited. Addressing these challenges, this paper proposes inclusive and incentivized personalized federated learning (iPFL), which incentivizes data holders with diverse purposes to collaboratively train personalized models without revealing raw data. iPFL constructs a model-sharing market by solving a graph-based training optimization and incorporates an incentive mechanism based on game theory principles. Theoretical analysis shows that iPFL adheres to two key incentive properties: individual rationality and truthfulness. Empirical studies on eleven AI tasks (e.g., large language models' instruction-following tasks) demonstrate that iPFL consistently achieves the highest economic utility, and better or comparable model performance compared to baseline methods. We anticipate that our iPFL can serve as a valuable technique for boosting future AI models on decentralized private data while making everyone satisfied. Social science/Science, technology and society Scientific community and society/Social sciences/Society Personalized Federated Learning Incentive Mechanism Data Full Text Additional Declarations There is NO Competing Interest. Cite Share Download PDF Status: Published Journal Publication published 25 Aug, 2025 Read the published version in Nature Communications → 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-3927659","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":272840567,"identity":"1e378115-e244-424a-a936-c707036e6ba4","order_by":0,"name":"Siheng Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA40lEQVRIiWNgGAWjYDACZh4wJcfAcADMJV6LMQPDYWK1MEC0JDZAVBOhRb6d9+Djgl926fMbzx+TYKiwTmxgP3sArxaDw3zJxjP7knM3HDjMJsFwJj2xgScvAb8WZh4zad6eA7kbGIBaGNsOJzZI8Bjgd1gzj/lvoJZ0+QaQln9EaGE4zGPGzPPjQAIDyGGMDURoMTjMYyzN25BsCPSLsUXCsXTjNp4cAg7rP2P4meePnbz8jIMPb3yosZbtZz9DwGEgwNgGJCQOMDAkAGk2wupB4A8Q8zcQp3YUjIJRMApGHgAAfjZBq54MN4gAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0001-6199-529X","institution":"Shanghai Jiao Tong University","correspondingAuthor":true,"prefix":"","firstName":"Siheng","middleName":"","lastName":"Chen","suffix":""},{"id":272840568,"identity":"17be7472-e464-42e2-907c-68922bf8d7a1","order_by":1,"name":"Enpei Zhang","email":"","orcid":"","institution":"Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Enpei","middleName":"","lastName":"Zhang","suffix":""},{"id":272840569,"identity":"68a6f9cd-f948-4952-a5c7-93d1ea012b9e","order_by":2,"name":"Jingyi Chai","email":"","orcid":"","institution":"Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Jingyi","middleName":"","lastName":"Chai","suffix":""},{"id":272840570,"identity":"b0a19885-8fbe-48a8-83f9-0ad7abe41ac7","order_by":3,"name":"Rui Ye","email":"","orcid":"","institution":"Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Rui","middleName":"","lastName":"Ye","suffix":""},{"id":272840571,"identity":"6f144294-1c38-486a-9a67-cb8bcaea1904","order_by":4,"name":"Yanfeng Wang","email":"","orcid":"","institution":"Shanghai Jiao Tong University","correspondingAuthor":false,"prefix":"","firstName":"Yanfeng","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2024-02-04 13:10:57","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3927659/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3927659/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41467-025-62959-5","type":"published","date":"2025-08-25T04:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":89888340,"identity":"9a78fa09-5730-485f-bfab-4c5a78588042","added_by":"auto","created_at":"2025-08-26 07:05:40","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3016848,"visible":true,"origin":"","legend":"","description":"","filename":"iPFLsubmission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3927659/v1_covered_540e0f5f-3fa7-40b7-89e3-f7534dee753f.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Incentivizing Inclusive Data Contributions in Personalized Federated Learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Personalized Federated Learning, Incentive Mechanism, Data","lastPublishedDoi":"10.21203/rs.3.rs-3927659/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3927659/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"While data plays a crucial role in training contemporary AI models, it is acknowledged that valuable public data will be exhausted in a few years, directing the world's attention towards the massive decentralized private data. However, the privacy-sensitive nature of raw data and lack of incentive mechanism prevent these valuable data from being fully exploited. Addressing these challenges, this paper proposes inclusive and incentivized personalized federated learning (iPFL), which incentivizes data holders with diverse purposes to collaboratively train personalized models without revealing raw data. iPFL constructs a model-sharing market by solving a graph-based training optimization and incorporates an incentive mechanism based on game theory principles. Theoretical analysis shows that iPFL adheres to two key incentive properties: individual rationality and truthfulness. Empirical studies on eleven AI tasks (e.g., large language models' instruction-following tasks) demonstrate that iPFL consistently achieves the highest economic utility, and better or comparable model performance compared to baseline methods. We anticipate that our iPFL can serve as a valuable technique for boosting future AI models on decentralized private data while making everyone satisfied.","manuscriptTitle":"Incentivizing Inclusive Data Contributions in Personalized Federated Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-02-23 02:56:20","doi":"10.21203/rs.3.rs-3927659/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"b73e6b08-aec5-4dc7-9c8b-cc247d3b4a09","owner":[],"postedDate":"February 23rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":28759322,"name":"Social science/Science, technology and society"},{"id":28759323,"name":"Scientific community and society/Social sciences/Society"}],"tags":[],"updatedAt":"2025-08-26T07:05:29+00:00","versionOfRecord":{"articleIdentity":"rs-3927659","link":"https://doi.org/10.1038/s41467-025-62959-5","journal":{"identity":"nature-communications","isVorOnly":false,"title":"Nature Communications"},"publishedOn":"2025-08-25 04:00:00","publishedOnDateReadable":"August 25th, 2025"},"versionCreatedAt":"2024-02-23 02:56:20","video":"","vorDoi":"10.1038/s41467-025-62959-5","vorDoiUrl":"https://doi.org/10.1038/s41467-025-62959-5","workflowStages":[]},"version":"v1","identity":"rs-3927659","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3927659","identity":"rs-3927659","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}