Local Back-Propagation: Layer-wise Unsupervised Learning in Forward-Forward Algorithms

Local Back-Propagation: Layer-wise Unsupervised Learning in Forward-Forward Algorithms | 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 Local Back-Propagation: Layer-wise Unsupervised Learning in Forward-Forward Algorithms Taewook Hwang, Hyein Seo, Sangkeun Jung This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5695830/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 Recent deep learning models, such as GPT-4, use the back-propagation algorithm (BP) and have achieved impressive performance. However, there is a noticeable difference between how BP operates and how the human brain learns. In response to this, the Forward-Forward algorithm (FF) was introduced. FF trains deep learning models using only forward passes. Although FF cannot fully replace BP due to its need for specialized inputs and loss functions, it remains promising in situations where BP is difficult to use, such as federated learning. To address these limitations and demonstrate the practical value of FF, we propose a Local Back-Propagation method that incorporates unsupervised FF. By using an unsupervised learning model, our approach allows training with standard inputs and common loss functions, thereby avoiding the special requirements of FF. This not only leads to more stable learning but also enables a wider range of possible applications than FF alone. Furthermore, because our method allows each layer to be physically separated, we have tested its effectiveness in scenarios like federated learning, where individual models are trained separately and then combined. Our results confirm that this approach expands the usability and scope of FF-based training methods. Back-propagation Forward-Forward algorithms Unsupervised learning Federated learning 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-5695830","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":396167568,"identity":"05597793-8ada-4699-aa48-4af2c2184d3d","order_by":0,"name":"Taewook Hwang","email":"","orcid":"","institution":"Chungnam National University","correspondingAuthor":false,"prefix":"","firstName":"Taewook","middleName":"","lastName":"Hwang","suffix":""},{"id":396167574,"identity":"af193fa5-47d9-419f-bdce-bc3b21bfc384","order_by":1,"name":"Hyein Seo","email":"","orcid":"","institution":"Chungnam National University","correspondingAuthor":false,"prefix":"","firstName":"Hyein","middleName":"","lastName":"Seo","suffix":""},{"id":396167577,"identity":"f777e09c-c8e3-49ba-acda-b03da6e073d5","order_by":2,"name":"Sangkeun Jung","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuUlEQVRIiWNgGAWjYBACAwhlA+MnEK0ljXQth0nQYi6RfnXDzx3n5c0lEhg//GBIyyeoxXJGTtnN3jO3DXfOSGCW7GHIsWwg6LAbOWk3eNtuJxjcSGCQZmCoMCBoC0jLzb9t50BamH8TqSX92G3etgMgLWxAW3KI0HLmDdtt2bZkww1nHrZZ9hikEaHlePqzm2/b7OQNjicfvvGjIpmwFgYGHpgixgZ4NBEA7A+IUjYKRsEoGAUjGAAAyRU9+M0HiLgAAAAASUVORK5CYII=","orcid":"","institution":"Chungnam National University","correspondingAuthor":true,"prefix":"","firstName":"Sangkeun","middleName":"","lastName":"Jung","suffix":""}],"badges":[],"createdAt":"2024-12-23 02:08:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5695830/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5695830/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":82548052,"identity":"45e98e57-ebad-4462-bcb6-3ee891defb16","added_by":"auto","created_at":"2025-05-12 19:01:33","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":508728,"visible":true,"origin":"","legend":"","description":"","filename":"NeuralProcessingLettersLocalBackprop.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5695830/v1_covered_e22d0613-6443-48d8-9669-ebca9c1c317b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Local Back-Propagation: Layer-wise Unsupervised Learning in Forward-Forward Algorithms","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Back-propagation, Forward-Forward algorithms, Unsupervised learning, Federated learning","lastPublishedDoi":"10.21203/rs.3.rs-5695830/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5695830/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eRecent deep learning models, such as GPT-4, use the back-propagation algorithm (BP) and have achieved impressive performance. However, there is a noticeable difference between how BP operates and how the human brain learns. In response to this, the Forward-Forward algorithm (FF) was introduced. FF trains deep learning models using only forward passes. Although FF cannot fully replace BP due to its need for specialized inputs and loss functions, it remains promising in situations where BP is difficult to use, such as federated learning. To address these limitations and demonstrate the practical value of FF, we propose a Local Back-Propagation method that incorporates unsupervised FF. By using an unsupervised learning model, our approach allows training with standard inputs and common loss functions, thereby avoiding the special requirements of FF. This not only leads to more stable learning but also enables a wider range of possible applications than FF alone. Furthermore, because our method allows each layer to be physically separated, we have tested its effectiveness in scenarios like federated learning, where individual models are trained separately and then combined. Our results confirm that this approach expands the usability and scope of FF-based training methods.\u003c/p\u003e","manuscriptTitle":"Local Back-Propagation: Layer-wise Unsupervised Learning in Forward-Forward Algorithms","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-01-02 02:17:04","doi":"10.21203/rs.3.rs-5695830/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":"4a670c37-6c7c-4c54-895c-75f73300afe5","owner":[],"postedDate":"January 2nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-05-12T18:53:22+00:00","versionOfRecord":[],"versionCreatedAt":"2025-01-02 02:17:04","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5695830","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5695830","identity":"rs-5695830","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}