ASGMamba: Adaptive Spectral Gating Mamba for Multivariate Time Series Forecasting

ASGMamba: Adaptive Spectral Gating Mamba for Multivariate Time Series Forecasting | 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 ASGMamba: Adaptive Spectral Gating Mamba for Multivariate Time Series Forecasting Qianyang Li, Xingjun Zhang, Shaoxun Wang, Jia Wei, Yueqi Xing This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8711886/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 Long-term multivariate time series forecasting (LTSF) plays a crucial role in various high-performance computing applications, including real-time energy grid management and large-scale traffic flow simulation. However, existing solutions face a dilemma: Transformer-based models suffer from quadratic complexity, limiting their scalability on long sequences, while linear State Space Models (SSMs) often struggle to distinguish valuable signals from high-frequency noise, leading to wasted state capacity. To bridge this gap, we propose ASGMamba, an efficient forecasting framework designed for resource-constrained supercomputing environments. ASGMamba integrates a lightweight Adaptive Spectral Gating (ASG) mechanism that dynamically filters noise based on local spectral energy, enabling the Mamba backbone to focus its state evolution on robust temporal dynamics. Furthermore, we introduce a hierarchical multi-scale architecture with variable-specific Node Embeddings to capture diverse physical characteristics. Extensive experiments on nine benchmarks demonstrate that ASGMamba achieves state-of-the-art accuracy. While keeping strictly O(L) complexity we significantly reduce the memory usage on long-horizon tasks, thus establishing ASGMamba as a scalable solution for high-throughput forecasting in resource limited environments.The code is available at https://github.com/hit636/ASGMamba Time Series Forecasting State Space Models Mamba Spectral Analysis 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-8711886","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":602794274,"identity":"5e943e83-3d76-499a-a27a-3e6ce368a9ab","order_by":0,"name":"Qianyang Li","email":"","orcid":"","institution":"Xi'an Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Qianyang","middleName":"","lastName":"Li","suffix":""},{"id":602794277,"identity":"3b74ff54-cf89-4cc1-a9e1-ab2e2987192f","order_by":1,"name":"Xingjun Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIie2RrQ7CMBSFLyHZzJbZLgvwCltmSPYym6oBNAKWq+rING+BRHZZ0pkR7CQYHAkWAWE/oEhKJaKfOD3ifuKkABrNX8KNNsdNad+huhICFMoKdEqC/bWC4ufl5XTfr+kuPwoCyyhB88ClioucBpuqnG+xMAhUNEFrEUsVB7ggNhPzDBplwIoEieX/GJIz98EENTrlqaA4zaVns1XsdAoqKC4KwxsxHjRbwmksaMismVzx6/LiXlk68ev8XN9W0SgzK7kChLdZ9CWG9zfJx2Cb6adoNBqN5psXHy5HqLs5Y2UAAAAASUVORK5CYII=","orcid":"","institution":"Xi'an Jiaotong University","correspondingAuthor":true,"prefix":"","firstName":"Xingjun","middleName":"","lastName":"Zhang","suffix":""},{"id":602794278,"identity":"3030adba-bc39-44cc-b91b-002cb2589898","order_by":2,"name":"Shaoxun Wang","email":"","orcid":"","institution":"Xi'an Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Shaoxun","middleName":"","lastName":"Wang","suffix":""},{"id":602794279,"identity":"3abc0eb5-9330-4d3f-ba51-ebde7ae4cf73","order_by":3,"name":"Jia Wei","email":"","orcid":"","institution":"Tsinghua University","correspondingAuthor":false,"prefix":"","firstName":"Jia","middleName":"","lastName":"Wei","suffix":""},{"id":602794283,"identity":"c442680d-2152-4aa2-b5bc-b751ce5cc797","order_by":4,"name":"Yueqi Xing","email":"","orcid":"","institution":"Shandong New Beiyang Information Technology Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"Yueqi","middleName":"","lastName":"Xing","suffix":""}],"badges":[],"createdAt":"2026-01-27 14:54:01","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8711886/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8711886/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105391726,"identity":"0c5799cf-fa39-4119-aaf8-e883f6687e5b","added_by":"auto","created_at":"2026-03-25 13:28:12","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":477102,"visible":true,"origin":"","legend":"","description":"","filename":"ASGMambaSupercomputing.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8711886/v1_covered_26274d35-3b09-405d-8f3a-dd1ac47bf9f1.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"ASGMamba: Adaptive Spectral Gating Mamba for Multivariate Time Series Forecasting","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":"Time Series Forecasting , State Space Models , Mamba , Spectral Analysis","lastPublishedDoi":"10.21203/rs.3.rs-8711886/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8711886/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eLong-term multivariate time series forecasting (LTSF) plays a crucial role in various high-performance computing applications, including real-time energy grid management and large-scale traffic flow simulation. However, existing solutions face a dilemma: Transformer-based models suffer from quadratic complexity, limiting their scalability on long sequences, while linear State Space Models (SSMs) often struggle to distinguish valuable signals from high-frequency noise, leading \u0026nbsp;to wasted state capacity. To bridge this gap, we propose ASGMamba, an efficient forecasting framework designed for resource-constrained supercomputing environments. ASGMamba integrates a lightweight Adaptive Spectral Gating \u0026nbsp;(ASG) mechanism that dynamically filters noise based on local spectral energy, enabling the Mamba backbone to focus its state evolution on robust temporal dynamics. Furthermore, we introduce a hierarchical multi-scale architecture with variable-specific Node Embeddings to capture diverse physical characteristics. Extensive experiments on nine benchmarks demonstrate that ASGMamba achieves state-of-the-art accuracy. While keeping strictly O(L) complexity we significantly reduce the memory usage on long-horizon tasks, thus establishing ASGMamba as a scalable solution for high-throughput forecasting in resource limited environments.The code is available at https://github.com/hit636/ASGMamba\u003c/p\u003e","manuscriptTitle":"ASGMamba: Adaptive Spectral Gating Mamba for Multivariate Time Series Forecasting","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-11 04:00:22","doi":"10.21203/rs.3.rs-8711886/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":"a8508d22-6b80-4793-8910-73b558bc3f97","owner":[],"postedDate":"March 11th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-25T13:27:07+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-11 04:00:22","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8711886","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8711886","identity":"rs-8711886","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}