Cross-Environment Transfer Learning for Robust mmWave Path Loss Modeling in 6G Wireless Networks

Cross-Environment Transfer Learning for Robust mmWave Path Loss Modeling in 6G Wireless Networks | 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 Cross-Environment Transfer Learning for Robust mmWave Path Loss Modeling in 6G Wireless Networks Samba Siva Reddy Mula, Vinay Kumar Pamula This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8685240/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 5 You are reading this latest preprint version Abstract Accurate millimeter-wave (mmWave) path loss modeling is critical for 6G and beyond wireless networks but remains challenging due to environment-dependent propagation effects and limited measurement data. This paper proposes a novel cross-environment transfer learning framework that combines parameter-based inductive transfer learning with structured pruning to enable robust and dataefficient path loss prediction across heterogeneous scenarios. The framework first trains a deep neural network on a data-rich source domain and selectively fine-tunes higher layers on a sparse target domain, preserving transferable propagation features while reducing computational cost. Structured pruning further removes low-importance neurons, resulting in a 38% reduction in trainable parameters with negligible accuracy loss. Experimental evaluation on multiple public mmWave datasets demonstrates that the proposed approach reduces root mean squared error (RMSE) by up to 15% and mean absolute error (MAE) by up to 12% compared to baseline neural networks, outperforming existing transfer learning strategies in both accuracy and efficiency. These results indicate that the hybrid transfer learning and pruning strategy provides an effective, scalable, and computationally feasible solution for cross-environment mmWave path loss modeling, with potential extensions to sub-terahertz networks and adaptive online learning scenarios. Millimeter-wave propagation Path loss modeling Transfer learning Cross-environment adaptation Hybrid physics–data modeling Structured pruning 6G wireless networks Sub-terahertz communications Full Text Supplementary Files DatasetA.csv DatasetB.csv DatasetC.csv snapacite.bst snaps.bst snarticle.tex snbasic.bst snchicago.bst snmathphysay.bst snnature.bst snvancouveray.bst snvancouvernum.bst trainingconvergence.pdf Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Major revision 19 Apr, 2026 Reviewers agreed at journal 13 Mar, 2026 Reviewers invited by journal 13 Mar, 2026 Editor assigned by journal 11 Feb, 2026 First submitted to journal 09 Feb, 2026 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-8685240","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":605624640,"identity":"1a6404df-67e2-463f-9fd5-6fe2a4df042b","order_by":0,"name":"Samba Siva Reddy Mula","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0001-8299-7059","institution":"JNTUK: Jawaharlal Nehru Technological University Kakinada","correspondingAuthor":true,"prefix":"","firstName":"Samba","middleName":"Siva Reddy","lastName":"Mula","suffix":""},{"id":605624641,"identity":"a95f3e91-3d0f-44ee-881e-77cc745a39be","order_by":1,"name":"Vinay Kumar Pamula","email":"","orcid":"","institution":"JNTUK: Jawaharlal Nehru Technological University Kakinada","correspondingAuthor":false,"prefix":"","firstName":"Vinay","middleName":"Kumar","lastName":"Pamula","suffix":""}],"badges":[],"createdAt":"2026-01-24 08:58:46","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8685240/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8685240/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104809073,"identity":"e89116cc-e775-41a7-bb0b-c2dd4b7d9a7a","added_by":"auto","created_at":"2026-03-17 12:47:15","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":473833,"visible":true,"origin":"","legend":"","description":"","filename":"CrossEnvironment.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8685240/v1_covered_52000e2d-e7db-4ac1-948a-0f1b2a056aad.pdf"},{"id":104683506,"identity":"8d9c0ba5-f62a-496a-913a-788f7ef1a0df","added_by":"auto","created_at":"2026-03-16 03:37:00","extension":"csv","order_by":13,"title":"","display":"","copyAsset":false,"role":"supplement","size":1162340,"visible":true,"origin":"","legend":"","description":"","filename":"DatasetA.csv","url":"https://assets-eu.researchsquare.com/files/rs-8685240/v1/b6660769f15d7265299272cb.csv"},{"id":104683516,"identity":"951eb768-0e19-44b1-8269-29ae304e3e51","added_by":"auto","created_at":"2026-03-16 03:37:00","extension":"csv","order_by":14,"title":"","display":"","copyAsset":false,"role":"supplement","size":192381,"visible":true,"origin":"","legend":"","description":"","filename":"DatasetB.csv","url":"https://assets-eu.researchsquare.com/files/rs-8685240/v1/05e0f0ffdcc1c9c8705e216a.csv"},{"id":104782420,"identity":"b53aa4d7-8786-4b7d-b9cb-5cf146eafd5f","added_by":"auto","created_at":"2026-03-17 07:57:16","extension":"csv","order_by":15,"title":"","display":"","copyAsset":false,"role":"supplement","size":93049,"visible":true,"origin":"","legend":"","description":"","filename":"DatasetC.csv","url":"https://assets-eu.researchsquare.com/files/rs-8685240/v1/ea61c9cd2a0dd0ca85d8ee47.csv"},{"id":104808486,"identity":"d7ac56be-055a-45e2-acd5-d83583ca0a18","added_by":"auto","created_at":"2026-03-17 12:38:03","extension":"bst","order_by":16,"title":"","display":"","copyAsset":false,"role":"supplement","size":146013,"visible":true,"origin":"","legend":"","description":"","filename":"snapacite.bst","url":"https://assets-eu.researchsquare.com/files/rs-8685240/v1/d99f331defb69e614c60a884.bst"},{"id":104683507,"identity":"be764694-f669-493e-874e-5945b843e8e0","added_by":"auto","created_at":"2026-03-16 03:37:00","extension":"bst","order_by":17,"title":"","display":"","copyAsset":false,"role":"supplement","size":29828,"visible":true,"origin":"","legend":"","description":"","filename":"snaps.bst","url":"https://assets-eu.researchsquare.com/files/rs-8685240/v1/26f93ea57fe2b7874e4a9371.bst"},{"id":104782074,"identity":"ccd00e30-6ad8-4bdf-bd0e-dbed73ee2158","added_by":"auto","created_at":"2026-03-17 07:56:48","extension":"tex","order_by":18,"title":"","display":"","copyAsset":false,"role":"supplement","size":38313,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.tex","url":"https://assets-eu.researchsquare.com/files/rs-8685240/v1/51c56f15d0c796ba5e3cec22.tex"},{"id":104782432,"identity":"5cc66004-bfec-405e-93a2-44014ffd6427","added_by":"auto","created_at":"2026-03-17 07:57:17","extension":"bst","order_by":19,"title":"","display":"","copyAsset":false,"role":"supplement","size":35515,"visible":true,"origin":"","legend":"","description":"","filename":"snbasic.bst","url":"https://assets-eu.researchsquare.com/files/rs-8685240/v1/1129c66bba7ab4256c632fec.bst"},{"id":104782879,"identity":"c16ecf4b-22fe-42a5-86e0-4ed045086118","added_by":"auto","created_at":"2026-03-17 07:57:54","extension":"bst","order_by":20,"title":"","display":"","copyAsset":false,"role":"supplement","size":33968,"visible":true,"origin":"","legend":"","description":"","filename":"snchicago.bst","url":"https://assets-eu.researchsquare.com/files/rs-8685240/v1/2d54572d110af00532accebe.bst"},{"id":104683512,"identity":"866b5c23-2146-4048-8536-11894267ce77","added_by":"auto","created_at":"2026-03-16 03:37:00","extension":"bst","order_by":21,"title":"","display":"","copyAsset":false,"role":"supplement","size":64023,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysay.bst","url":"https://assets-eu.researchsquare.com/files/rs-8685240/v1/f469b79ce1ea0997ecf3b45f.bst"},{"id":104683511,"identity":"4d06d5c8-15c4-4f4f-a8bc-d0d21a04bba6","added_by":"auto","created_at":"2026-03-16 03:37:00","extension":"bst","order_by":22,"title":"","display":"","copyAsset":false,"role":"supplement","size":37333,"visible":true,"origin":"","legend":"","description":"","filename":"snnature.bst","url":"https://assets-eu.researchsquare.com/files/rs-8685240/v1/04cdb15309f7d789284f99d6.bst"},{"id":104683509,"identity":"6c2ca9ba-9dab-4f94-b6b8-e76e95d20381","added_by":"auto","created_at":"2026-03-16 03:37:00","extension":"bst","order_by":23,"title":"","display":"","copyAsset":false,"role":"supplement","size":39951,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouveray.bst","url":"https://assets-eu.researchsquare.com/files/rs-8685240/v1/830db29f0de97f80453a996e.bst"},{"id":104782355,"identity":"1bc94aef-6160-443d-abcd-c0d21d0157ea","added_by":"auto","created_at":"2026-03-17 07:57:12","extension":"bst","order_by":24,"title":"","display":"","copyAsset":false,"role":"supplement","size":40758,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouvernum.bst","url":"https://assets-eu.researchsquare.com/files/rs-8685240/v1/12e5ce9f38f2d437119db248.bst"},{"id":104683515,"identity":"6d02f489-fc54-4ba0-869b-3f7071f530d4","added_by":"auto","created_at":"2026-03-16 03:37:00","extension":"pdf","order_by":25,"title":"","display":"","copyAsset":false,"role":"supplement","size":33392,"visible":true,"origin":"","legend":"","description":"","filename":"trainingconvergence.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8685240/v1/7acaf48e9104e24764da0490.pdf"}],"financialInterests":"","formattedTitle":"Cross-Environment Transfer Learning for Robust mmWave Path Loss Modeling in 6G Wireless Networks","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"eurasip-journal-on-wireless-communications-and-networking","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jwcn","sideBox":"Learn more about [EURASIP Journal on Wireless Communications and Networking](http://jwcn-eurasipjournals.springeropen.com)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/jwcn/default.aspx","title":"EURASIP Journal on Wireless Communications and Networking","twitterHandle":"@SpringerEng","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Millimeter-wave propagation, Path loss modeling, Transfer learning, Cross-environment adaptation, Hybrid physics–data modeling, Structured pruning, 6G wireless networks, Sub-terahertz communications","lastPublishedDoi":"10.21203/rs.3.rs-8685240/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8685240/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate millimeter-wave (mmWave) path loss modeling is critical for 6G and beyond wireless networks but remains challenging due to environment-dependent propagation effects and limited measurement data. This paper proposes a novel cross-environment transfer learning framework that combines parameter-based inductive transfer learning with structured pruning to enable robust and dataefficient path loss prediction across heterogeneous scenarios. The framework first trains a deep neural network on a data-rich source domain and selectively fine-tunes higher layers on a sparse target domain, preserving transferable propagation features while reducing computational cost. Structured pruning further removes low-importance neurons, resulting in a 38% reduction in trainable parameters with negligible accuracy loss. Experimental evaluation on multiple public mmWave datasets demonstrates that the proposed approach reduces root mean squared error (RMSE) by up to 15% and mean absolute error (MAE) by up to 12% compared to baseline neural networks, outperforming existing transfer learning strategies in both accuracy and efficiency. These results indicate that the hybrid transfer learning and pruning strategy provides an effective, scalable, and computationally feasible solution for cross-environment mmWave path loss modeling, with potential extensions to sub-terahertz networks and adaptive online learning scenarios.","manuscriptTitle":"Cross-Environment Transfer Learning for Robust mmWave Path Loss Modeling in 6G Wireless Networks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-16 03:36:42","doi":"10.21203/rs.3.rs-8685240/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revision","date":"2026-04-20T00:03:02+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"","date":"2026-03-13T13:36:14+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-13T11:34:13+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-11T05:21:52+00:00","index":"","fulltext":""},{"type":"submitted","content":"EURASIP Journal on Wireless Communications and Networking","date":"2026-02-10T03:39:01+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"eurasip-journal-on-wireless-communications-and-networking","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jwcn","sideBox":"Learn more about [EURASIP Journal on Wireless Communications and Networking](http://jwcn-eurasipjournals.springeropen.com)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/jwcn/default.aspx","title":"EURASIP Journal on Wireless Communications and Networking","twitterHandle":"@SpringerEng","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"6c53ebfa-19b0-4a03-9e3e-2b6885b4b8e1","owner":[],"postedDate":"March 16th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-04-20T04:03:13+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-16 03:36:42","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8685240","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8685240","identity":"rs-8685240","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}