FedContrast: A Contrastive Learning Framework to Mitigate Client Drift Under Statistical Heterogeneity in Federated Multi-Class Soil Classification

FedContrast: A Contrastive Learning Framework to Mitigate Client Drift Under Statistical Heterogeneity in Federated Multi-Class Soil Classification | 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 FedContrast: A Contrastive Learning Framework to Mitigate Client Drift Under Statistical Heterogeneity in Federated Multi-Class Soil Classification Aviral Kumar Goyal, Manish Pandey, Dhirendra Pratap Singh, Jaytrilok Choudhary, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6774369/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 FedContrast is a novel contrastive learning framework designed to improve federated classification performance under statistical heterogeneity through representation alignment techniques. It was implemented on two complementary soil image datasets: JPSID (1,563 samples, 4 soil types) and PSST (163 samples, 5 soil types), collected from agricultural and environmental monitoring contexts. Classification performance was evaluated under both IID and Dirichlet-induced non-IID settings, with concentration parameters \(\alpha = 0.5\) and \(\alpha = 1.0\) , across client configurations of \(K = 5\) and \(K = 10\) . For non-IID setups, the InceptionV3 model was selected with a batch size \(B = 32\) and communication rounds \(T = 100\) , as it consistently outperformed VGG19, Xception, and MobileNetV2 even under IID conditions. Evaluation results show that FedContrast outperformed traditional FL methods, achieving 88.8% accuracy, 88.8% F1-score, 89.9% precision, and 87.7% recall on the JPSID dataset under extreme heterogeneity ( $ K = 10 $ , $ \alpha = 0.5 $ ). On the PSST dataset, FedContrast maintained superior performance with a total loss ( \(\mathcal{L}_\text{total}\) ) of 0.367 ( $ K = 5 $ , $ \alpha = 1.0 $ ) and 0.338 ( $ K = 10 $ , $ \alpha = 1.0 $ ), reflecting a 15--45% improvement over traditional FL methods such as FedAvg, MOON, FedSGD, and FedProx. Federated Learning Contrastive Learning Statistical Heterogeneity Dirichlet Distribution Client Drift Mitigation Representation Alignment Soil Classification Temperature Scaling Feature Extraction Full Text Additional Declarations No competing interests reported. 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-6774369","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":467142174,"identity":"5f4f215b-2d1d-4fd5-a414-3c07308f2165","order_by":0,"name":"Aviral Kumar Goyal","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABCklEQVRIiWNgGAWjYFACxgYGhgII60BChQ2IbjxAWIsBhHngw5k0sAgBLSAA1XJwZtthiF58ivlnJLd9+GHAYNcvkfzgMM+Z83Zr2w8DbamxicalReJGYvPMHgOG5Jkz0gwO81TcTt52JhGo5VhabgMuPWcONjPwALUY3EgAajlzO9nsAFALY8NhnFrkgVoY/4C1pH84zNt2Ltns/EP8WgyONzYzA22xM7iRYwD0/gE7sxsEbDEEaZExkEiQ7HlTAAzk5ASzG0BbEvD4Re4w+2PGNxU29vzs6RsfJFTY2ZudT3/44EONDW7vQ4BEYoNAApiVCFaZgF85GNgz8B+AMkbBKBgFo2AUoAEApzRqdtBA270AAAAASUVORK5CYII=","orcid":"","institution":"Maulana Azad National Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Aviral","middleName":"Kumar","lastName":"Goyal","suffix":""},{"id":467142175,"identity":"dcf5eedd-429a-421a-a2c8-9fb37498cfbc","order_by":1,"name":"Manish Pandey","email":"","orcid":"","institution":"Maulana Azad National Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Manish","middleName":"","lastName":"Pandey","suffix":""},{"id":467142176,"identity":"166d0b9a-c5dc-49a0-ad6f-a59746c56f1c","order_by":2,"name":"Dhirendra Pratap Singh","email":"","orcid":"","institution":"Maulana Azad National Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Dhirendra","middleName":"Pratap","lastName":"Singh","suffix":""},{"id":467142177,"identity":"b14a1c1c-44e4-4bee-a30b-7f7dd23c3b5c","order_by":3,"name":"Jaytrilok Choudhary","email":"","orcid":"","institution":"Maulana Azad National Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Jaytrilok","middleName":"","lastName":"Choudhary","suffix":""},{"id":467142178,"identity":"486e100e-1910-4be8-81da-2b68ec89391a","order_by":4,"name":"Rahul Haripriya","email":"","orcid":"","institution":"Maulana Azad National Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Rahul","middleName":"","lastName":"Haripriya","suffix":""}],"badges":[],"createdAt":"2025-05-29 08:23:24","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6774369/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6774369/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":84282937,"identity":"f4c42b74-0165-4c62-bc3e-cf7a630ab4d7","added_by":"auto","created_at":"2025-06-10 07:05:07","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1549019,"visible":true,"origin":"","legend":"","description":"","filename":"FedContrastManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6774369/v1_covered_57d0f485-c1cf-440f-b238-55b181885fbf.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"FedContrast: A Contrastive Learning Framework to Mitigate Client Drift Under Statistical Heterogeneity in Federated Multi-Class Soil Classification","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","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, Contrastive Learning, Statistical Heterogeneity, Dirichlet Distribution, Client Drift Mitigation, Representation Alignment, Soil Classification, Temperature Scaling, Feature Extraction","lastPublishedDoi":"10.21203/rs.3.rs-6774369/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6774369/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eFedContrast is a novel contrastive learning framework designed to improve federated classification performance under statistical heterogeneity through representation alignment techniques. It was implemented on two complementary soil image datasets: JPSID (1,563 samples, 4 soil types) and PSST (163 samples, 5 soil types), collected from agricultural and environmental monitoring contexts. Classification performance was evaluated under both IID and Dirichlet-induced non-IID settings, with concentration parameters \u003cspan class=\"InlineEquation\"\u003e \u003cspan class=\"mathinline\"\u003e \\(\\alpha = 0.5\\) \u003c/span\u003e \u003c/span\u003e and \u003cspan class=\"InlineEquation\"\u003e \u003cspan class=\"mathinline\"\u003e \\(\\alpha = 1.0\\) \u003c/span\u003e \u003c/span\u003e, across client configurations of \u003cspan class=\"InlineEquation\"\u003e \u003cspan class=\"mathinline\"\u003e \\(K = 5\\) \u003c/span\u003e \u003c/span\u003e and \u003cspan class=\"InlineEquation\"\u003e \u003cspan class=\"mathinline\"\u003e \\(K = 10\\) \u003c/span\u003e \u003c/span\u003e. For non-IID setups, the InceptionV3 model was selected with a batch size \u003cspan class=\"InlineEquation\"\u003e \u003cspan class=\"mathinline\"\u003e \\(B = 32\\) \u003c/span\u003e \u003c/span\u003e and communication rounds \u003cspan class=\"InlineEquation\"\u003e \u003cspan class=\"mathinline\"\u003e \\(T = 100\\) \u003c/span\u003e \u003c/span\u003e, as it consistently outperformed VGG19, Xception, and MobileNetV2 even under IID conditions. Evaluation results show that FedContrast outperformed traditional FL methods, achieving 88.8% accuracy, 88.8% F1-score, 89.9% precision, and 87.7% recall on the JPSID dataset under extreme heterogeneity (\u003cspan\u003e$\u003c/span\u003eK = 10\u003cspan\u003e$\u003c/span\u003e, \u003cspan\u003e$\u003c/span\u003e\\alpha = 0.5\u003cspan\u003e$\u003c/span\u003e). On the PSST dataset, FedContrast maintained superior performance with a total loss (\u003cspan class=\"InlineEquation\"\u003e \u003cspan class=\"mathinline\"\u003e \\(\\mathcal{L}_\\text{total}\\) \u003c/span\u003e \u003c/span\u003e) of 0.367 (\u003cspan\u003e$\u003c/span\u003eK = 5\u003cspan\u003e$\u003c/span\u003e, \u003cspan\u003e$\u003c/span\u003e\\alpha = 1.0\u003cspan\u003e$\u003c/span\u003e) and 0.338 (\u003cspan\u003e$\u003c/span\u003eK = 10\u003cspan\u003e$\u003c/span\u003e, \u003cspan\u003e$\u003c/span\u003e\\alpha = 1.0\u003cspan\u003e$\u003c/span\u003e), reflecting a 15--45% improvement over traditional FL methods such as FedAvg, MOON, FedSGD, and FedProx.\u003c/p\u003e","manuscriptTitle":"FedContrast: A Contrastive Learning Framework to Mitigate Client Drift Under Statistical Heterogeneity in Federated Multi-Class Soil Classification","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-10 06:55:43","doi":"10.21203/rs.3.rs-6774369/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":"337afa1a-54fa-4b74-9528-0ade8b5060da","owner":[],"postedDate":"June 10th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-06-10T06:55:43+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-10 06:55:43","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6774369","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6774369","identity":"rs-6774369","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}