Tri-Module Deep DFT Architecture with Physical Regularization, Task Coupling, and Compression-Based Transferability

Tri-Module Deep DFT Architecture with Physical Regularization, Task Coupling, and Compression-Based Transferability | 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 Tri-Module Deep DFT Architecture with Physical Regularization, Task Coupling, and Compression-Based Transferability Abdelaali Mahrouk This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7264403/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 We introduce a deep learning architecture designed to enhance Density Functional Theory (DFT) property prediction through a tri-module system combining task decoupling, physics-based regularization, and compression-based transferability. The proposed framework consists of a shared backbone followed by three dedicated heads for energy, force, and polarizability predictions. A physically inspired Jacobian regularizer enforces structural consistency across outputs, while a bottleneck-based latent space is used to compress task-relevant features and enable inter-task knowledge transfer. Our design allows for minimal interference between learning objectives while preserving physical alignment, especially under low-data or high-noise conditions. This architecture aims to improve generalization, interpretability, and adaptability in multi-task DFT-based modeling without compromising computational efficiency. Early results suggest robust performance across benchmarks and a scalable foundation for future cross-property extensions. Physical sciences/Engineering Physical sciences/Materials science Physical sciences/Mathematics and computing Physical sciences/Physics 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-7264403","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":500971394,"identity":"de0790db-2dd7-462a-97c5-05fd4c763a36","order_by":0,"name":"Abdelaali Mahrouk","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA50lEQVRIiWNgGAWjYDACCQYDCM3e//ABkObhI14LzxlmEIuHjXgtEjlsEiAGQS38s5s3MN2ouScn2ZB7rPJrjp0MGwPzw0c38Fly51gBc86xYmNphnNpt2W3JQMdxmZsnIPPmhs5Bsw5bAmJ8xgbzG5LbmMGauFhk8anRR6s5R9QCzODWbHktnrCWgxAWnLbEhJns/GYMX7cdpiwFkOgXw7n9iUYS/awJUszbjvOw8ZMwC9yt5s3Ps75liAncf/xwY8/t1Xb87M3P3yM1/tAcADGYOYBkwSUowDGH6SoHgWjYBSMghEDANK7RMmeO71bAAAAAElFTkSuQmCC","orcid":"","institution":"Independent","correspondingAuthor":true,"prefix":"","firstName":"Abdelaali","middleName":"","lastName":"Mahrouk","suffix":""}],"badges":[],"createdAt":"2025-07-31 16:53:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7264403/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7264403/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93700756,"identity":"847ed7e2-886d-4397-a315-3ce7f2ff201a","added_by":"auto","created_at":"2025-10-16 15:32:04","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":763128,"visible":true,"origin":"","legend":"","description":"","filename":"DFTtris.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7264403/v1_covered_762c3c5c-6667-4525-88b4-29d3b1325c3b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eTri-Module Deep DFT Architecture with Physical Regularization, Task Coupling, and Compression-Based Transferability\u003c/p\u003e","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":"","lastPublishedDoi":"10.21203/rs.3.rs-7264403/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7264403/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eWe introduce a deep learning architecture designed to enhance Density Functional Theory (DFT) property prediction through a tri-module system combining task decoupling, physics-based regularization, and compression-based transferability. The proposed framework consists of a shared backbone followed by three dedicated heads for energy, force, and polarizability predictions. A physically inspired Jacobian regularizer enforces structural consistency across outputs, while a bottleneck-based latent space is used to compress task-relevant features and enable inter-task knowledge transfer. Our design allows for minimal interference between learning objectives while preserving physical alignment, especially under low-data or high-noise conditions. This architecture aims to improve generalization, interpretability, and adaptability in multi-task DFT-based modeling without compromising computational efficiency. Early results suggest robust performance across benchmarks and a scalable foundation for future cross-property extensions.\u003c/p\u003e","manuscriptTitle":"Tri-Module Deep DFT Architecture with Physical Regularization, Task Coupling, and Compression-Based Transferability","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-22 14:19:11","doi":"10.21203/rs.3.rs-7264403/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":"4d18606a-ffb3-49db-ac96-a6fe6400db33","owner":[],"postedDate":"August 22nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":53576746,"name":"Physical sciences/Engineering"},{"id":53576747,"name":"Physical sciences/Materials science"},{"id":53576748,"name":"Physical sciences/Mathematics and computing"},{"id":53576749,"name":"Physical sciences/Physics"}],"tags":[],"updatedAt":"2025-10-16T15:23:53+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-22 14:19:11","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7264403","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7264403","identity":"rs-7264403","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}