Integration of a GNN and U-Net for Hybrid Beamforming in mm-Wave m-MIMO Systems

Integration of a GNN and U-Net for Hybrid Beamforming in mm-Wave m-MIMO Systems | 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 Integration of a GNN and U-Net for Hybrid Beamforming in mm-Wave m-MIMO Systems Gurpreet Kaur, Gurmeet Kaur This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7224350/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 15 Dec, 2025 Read the published version in Wireless Personal Communications → Version 1 posted 13 You are reading this latest preprint version Abstract Millimeter-Wave (mm-Wave) based Massive Multiple-Input Multiple-Output massive (m-MIMO) systems promise high data rates and high spectral efficiency in next-generation i.e., beyond fifth generation (B5G) wireless networks. Moreover, the fully-digital precoding technique helps further to achieve the highest spectral efficiency in mm-Wave massive MIMO systems but face significant challenges such as hardware complexity and cost. Practically, these systems are infeasible due to complexity and cost of using radio frequency (RF) chain with each antenna in such systems. Hybrid beamforming emerges as a practical solution by combining analog and digital precoding, yet its performance hinges on accurate and low-complexity beamformer design under sparse and dynamic channel conditions. This paper proposes a novel deep learning approach that synergizes Graph Neural Networks (GNNs) and U-Net architectures to efficiently learn optimal hybrid beamforming strategies from channel state information (CSI). For generalizing the system in various configurations and distributions, the GNN is used to capture the spatial and topological relationships between antennas and users. Simultaneously, for extracting the various spatial features for enhanced precoder rebuilding, the U-Net is used to process the structured CSI representations. The proposed approach is trained using a loss function for optimizing the spectral efficiency (SE) and bit error rate (BER). Simulation results show that the integrated GNN and U-Net model achieves superior performance to traditional methods, with significantly reduced computational overhead during inference. The SE percentage improvement with proposed approach is varying from 9–54% as compared to some exiting techniques. Moreover, the proposed approach is able to achieve approximately 92% of the fully digital precoding performance. Millimeter-Wave (mm-Wave) Massive Multiple-Input Multiple-Output (m-MIMO) Hybrid Beamforming Graph Neural Network (GNN) U-Net Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 15 Dec, 2025 Read the published version in Wireless Personal Communications → Version 1 posted Editorial decision: Revision requested 13 Nov, 2025 Reviews received at journal 01 Nov, 2025 Reviews received at journal 07 Oct, 2025 Reviews received at journal 19 Sep, 2025 Reviewers agreed at journal 19 Sep, 2025 Reviewers agreed at journal 19 Sep, 2025 Reviews received at journal 15 Sep, 2025 Reviewers agreed at journal 15 Sep, 2025 Reviewers agreed at journal 14 Sep, 2025 Reviewers invited by journal 14 Sep, 2025 Editor assigned by journal 01 Aug, 2025 Submission checks completed at journal 01 Aug, 2025 First submitted to journal 27 Jul, 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-7224350","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":517731876,"identity":"00c3efc9-9606-477f-9741-db2c88692eb2","order_by":0,"name":"Gurpreet Kaur","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7UlEQVRIiWNgGAWjYDADCRDxwUCCB5mPXwdICeMMoBYekrQwg5TzEFIqH5H77HFFhU2dZPsZs882BRYy9hIJjB9+MFjk4dJieCPd3PDMmTQJaZ4c49k5IIdJJDBL9jBIFOPUMiONTbKx7bCEHEOOMTNUC4M00KWJDXi1/PsvIcf/xpjZAmrLb3xa5CVAWhoOSEhLAG1hgGhhw2uLAc8zdsOGY8mSM2c8K2bsAWk587DNEsjAbUt7GtvDhho7fonzyZsZfvyps2dvTz5840dFHW5bDjCwoYsxAhUb4FAPsqUBU8soGAWjYBSMAlQAAOhtRBze07VVAAAAAElFTkSuQmCC","orcid":"","institution":"Indian Institute of Information Technology Una","correspondingAuthor":true,"prefix":"","firstName":"Gurpreet","middleName":"","lastName":"Kaur","suffix":""},{"id":517731877,"identity":"c798a6fe-30a1-4933-a7de-bdcf5c6fbef7","order_by":1,"name":"Gurmeet Kaur","email":"","orcid":"","institution":"Punjabi University","correspondingAuthor":false,"prefix":"","firstName":"Gurmeet","middleName":"","lastName":"Kaur","suffix":""}],"badges":[],"createdAt":"2025-07-27 06:08:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7224350/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7224350/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11277-025-11889-y","type":"published","date":"2025-12-15T15:57:21+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":91821840,"identity":"6d97f0b4-37c7-4d23-81ee-4217f67f8b2d","added_by":"auto","created_at":"2025-09-22 07:36:29","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":220710,"visible":true,"origin":"","legend":"","description":"","filename":"Revised1.docx","url":"https://assets-eu.researchsquare.com/files/rs-7224350/v1/0ba08f735e823f094b8461fa.docx"},{"id":91821838,"identity":"d52fd3d8-10c7-4864-ae1d-5c2b5dfbfd88","added_by":"auto","created_at":"2025-09-22 07:36:29","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4489,"visible":true,"origin":"","legend":"","description":"","filename":"5881a4d8c4df4f09b0096d46bd2eb27c.json","url":"https://assets-eu.researchsquare.com/files/rs-7224350/v1/63e7b025d26e1ebbdfa8dd41.json"},{"id":91821599,"identity":"5ea8a72e-62b1-4a6e-9205-222f0d72ede3","added_by":"auto","created_at":"2025-09-22 07:28:29","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":87440,"visible":true,"origin":"","legend":"","description":"","filename":"5881a4d8c4df4f09b0096d46bd2eb27c1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7224350/v1/406f8dded305f65fae778920.xml"},{"id":91821596,"identity":"3ed405a1-17f5-4ebd-8d4a-a84dfe06229b","added_by":"auto","created_at":"2025-09-22 07:28:29","extension":"emf","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":72108,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.emf","url":"https://assets-eu.researchsquare.com/files/rs-7224350/v1/11cf3b749b88e6b268a51fbc.emf"},{"id":91821594,"identity":"c4dc56b4-d84d-4a8f-bb93-f95e909a5f35","added_by":"auto","created_at":"2025-09-22 07:28:29","extension":"emf","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":99372,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.emf","url":"https://assets-eu.researchsquare.com/files/rs-7224350/v1/3b6384e88b7c768fc021daf4.emf"},{"id":91821593,"identity":"58508a6c-3c16-4f0d-8a85-9b16e5f25e7e","added_by":"auto","created_at":"2025-09-22 07:28:29","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55043,"visible":true,"origin":"","legend":"","description":"","filename":"groupimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7224350/v1/419277f757e0c713c2493160.jpeg"},{"id":91822682,"identity":"74a264fd-d14c-4cde-a3cb-6516ec8778df","added_by":"auto","created_at":"2025-09-22 07:44:29","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":22830,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7224350/v1/f5987faf18a450077bcd434b.png"},{"id":91821839,"identity":"cf77615b-e97e-4e70-becc-4d62d36b9741","added_by":"auto","created_at":"2025-09-22 07:36:29","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20582,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7224350/v1/613e91b15c4f9e9d3ac80cf5.png"},{"id":91821601,"identity":"ed750185-fa8d-4e20-a61d-8b226c9d08bb","added_by":"auto","created_at":"2025-09-22 07:28:29","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15631,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinegroupimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7224350/v1/13b6965f747026ad28af5a3f.png"},{"id":91821842,"identity":"8ebc2947-44fc-4101-aad6-839e1ac571e5","added_by":"auto","created_at":"2025-09-22 07:36:29","extension":"xml","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":84608,"visible":true,"origin":"","legend":"","description":"","filename":"5881a4d8c4df4f09b0096d46bd2eb27c1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7224350/v1/f470c0488cd50e3bbe20c05b.xml"},{"id":91821603,"identity":"e827b3bd-261d-4bcc-9a04-616ff0b78b69","added_by":"auto","created_at":"2025-09-22 07:28:29","extension":"html","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":101905,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7224350/v1/3ccd357ed5536a54d217a7ef.html"},{"id":98814215,"identity":"c3256ed4-dddc-44df-a4ca-e866e390586a","added_by":"auto","created_at":"2025-12-22 16:11:55","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":510290,"visible":true,"origin":"","legend":"","description":"","filename":"Revised1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7224350/v1_covered_5725cb8d-33e4-4b24-bda1-cbf84de696b7.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Integration of a GNN and U-Net for Hybrid Beamforming in mm-Wave m-MIMO Systems","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":"wireless-personal-communications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"wire","sideBox":"Learn more about [Wireless Personal Communications](https://www.springer.com/journal/11277)","snPcode":"11277","submissionUrl":"https://submission.nature.com/new-submission/11277/3","title":"Wireless Personal Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Millimeter-Wave (mm-Wave), Massive Multiple-Input Multiple-Output (m-MIMO), Hybrid Beamforming, Graph Neural Network (GNN), U-Net","lastPublishedDoi":"10.21203/rs.3.rs-7224350/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7224350/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eMillimeter-Wave (mm-Wave) based Massive Multiple-Input Multiple-Output massive (m-MIMO) systems promise high data rates and high spectral efficiency in next-generation i.e., beyond fifth generation (B5G) wireless networks. Moreover, the fully-digital precoding technique helps further to achieve the highest spectral efficiency in mm-Wave massive MIMO systems but face significant challenges such as hardware complexity and cost. Practically, these systems are infeasible due to complexity and cost of using radio frequency (RF) chain with each antenna in such systems. Hybrid beamforming emerges as a practical solution by combining analog and digital precoding, yet its performance hinges on accurate and low-complexity beamformer design under sparse and dynamic channel conditions. This paper proposes a novel deep learning approach that synergizes Graph Neural Networks (GNNs) and U-Net architectures to efficiently learn optimal hybrid beamforming strategies from channel state information (CSI). For generalizing the system in various configurations and distributions, the GNN is used to capture the spatial and topological relationships between antennas and users. Simultaneously, for extracting the various spatial features for enhanced precoder rebuilding, the U-Net is used to process the structured CSI representations. The proposed approach is trained using a loss function for optimizing the spectral efficiency (SE) and bit error rate (BER). Simulation results show that the integrated GNN and U-Net model achieves superior performance to traditional methods, with significantly reduced computational overhead during inference. The SE percentage improvement with proposed approach is varying from 9\u0026ndash;54% as compared to some exiting techniques. Moreover, the proposed approach is able to achieve approximately 92% of the fully digital precoding performance.\u003c/p\u003e","manuscriptTitle":"Integration of a GNN and U-Net for Hybrid Beamforming in mm-Wave m-MIMO Systems","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-22 07:28:24","doi":"10.21203/rs.3.rs-7224350/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-11-13T20:48:10+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-01T20:45:35+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-07T12:59:19+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-19T11:15:10+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"169111243905728283811017959160824193497","date":"2025-09-19T10:52:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"58307683357712905581752585100977265813","date":"2025-09-19T08:24:40+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-15T09:47:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"154262281735601858284628637423963619650","date":"2025-09-15T08:44:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"324149638748417337427523178002352325826","date":"2025-09-14T13:27:36+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-14T10:24:59+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-01T13:27:44+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-01T13:27:15+00:00","index":"","fulltext":""},{"type":"submitted","content":"Wireless Personal Communications","date":"2025-07-27T05:56:50+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"wireless-personal-communications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"wire","sideBox":"Learn more about [Wireless Personal Communications](https://www.springer.com/journal/11277)","snPcode":"11277","submissionUrl":"https://submission.nature.com/new-submission/11277/3","title":"Wireless Personal Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"113e5c65-86a8-49c7-9eea-237c8ac9e84e","owner":[],"postedDate":"September 22nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-12-22T16:05:54+00:00","versionOfRecord":{"articleIdentity":"rs-7224350","link":"https://doi.org/10.1007/s11277-025-11889-y","journal":{"identity":"wireless-personal-communications","isVorOnly":false,"title":"Wireless Personal Communications"},"publishedOn":"2025-12-15 15:57:21","publishedOnDateReadable":"December 15th, 2025"},"versionCreatedAt":"2025-09-22 07:28:24","video":"","vorDoi":"10.1007/s11277-025-11889-y","vorDoiUrl":"https://doi.org/10.1007/s11277-025-11889-y","workflowStages":[]},"version":"v1","identity":"rs-7224350","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7224350","identity":"rs-7224350","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}