Multivariate Time Series Anomaly Detection for Over-reconstruction of Anomalous Data

Multivariate Time Series Anomaly Detection for Over-reconstruction of Anomalous Data | 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 Multivariate Time Series Anomaly Detection for Over-reconstruction of Anomalous Data Youmeng Li, Jun Kong, Min Jiang, Xuefeng Tao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6646658/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 30 Mar, 2026 Read the published version in International Journal of Machine Learning and Cybernetics → Version 1 posted 11 You are reading this latest preprint version Abstract Anomaly detection in multivariate time series (MTS) data is vital for maintaining system stability and safety. Current reconstruction-based methods aim to learn the normal patterns of data. However, these methods often suffer from the model's over-generalization and the polluted training set, leading to the over-reconstruction of anomalous data. To address these issues, we propose MTAD-ORe, an unsupervised MTS Anomaly Detection framework for Over-Reconstruction of anomalous data. Firstly, to alleviate the model's over-generalization, we design the Gated Diversity Memory Module (GDMM) and the Cross Fusion Module (CFM). GDMM designs a memory block to store typical and diverse features of normal data, which is used for bidirectional updating with the input data. This makes the reconstructed results of anomalous data resemble normal data. Meanwhile, to prevent information loss during the bidirectional updates, CFM is designed to integrate feature information. Secondly, to calibrate the learning bias caused by the polluted training set, we design the Pollution Calibration Strategy (PCS). PCS creates a more reasonable objective for MTAD-ORe, which leads MTAD-ORe to concentrate more on plausible normal data. Experimental studies on four public datasets demonstrate that our MTAD-ORe outperforms several existing competitive baselines. Unsupervised anomaly detection over-reconstruction of anomalous data gated diversity memory module (GDMM) pollution calibration strategy (PCS) Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 30 Mar, 2026 Read the published version in International Journal of Machine Learning and Cybernetics → Version 1 posted Editorial decision: Revision requested 22 Aug, 2025 Reviews received at journal 26 Jun, 2025 Reviews received at journal 19 Jun, 2025 Reviews received at journal 09 Jun, 2025 Reviewers agreed at journal 05 Jun, 2025 Reviewers agreed at journal 04 Jun, 2025 Reviewers agreed at journal 02 Jun, 2025 Reviewers invited by journal 02 Jun, 2025 Editor assigned by journal 19 May, 2025 Submission checks completed at journal 14 May, 2025 First submitted to journal 12 May, 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-6646658","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":465791039,"identity":"a7f1cd9f-73ec-4a46-b444-3c5e2f53b292","order_by":0,"name":"Youmeng Li","email":"","orcid":"","institution":"Jiangnan University","correspondingAuthor":false,"prefix":"","firstName":"Youmeng","middleName":"","lastName":"Li","suffix":""},{"id":465791040,"identity":"2767f51b-36af-4ced-b4b6-2cdb189f8881","order_by":1,"name":"Jun Kong","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/0lEQVRIiWNgGAWjYBACCSghx9iMEDQgSosxiVqAILEBSRC/Fsn23sMvLNvupDe3Mz97+HWHXR4De/M2CYaaOzi1SPOcS7OQbHuW29jMZm4seya5mIHnWJkEw7FnOLXISeSYGUi2HQZqYTCTlmxjTmwAikgwNhwmqCWdsZn9G1BLfWKD/Bv8WqQlcowfALUkMDbzmEl+bDsMtIUHvxbJnjNmDBLnDhs2NvOUSTO2HU9s40krtkg4hluLxPEe488SZYflDfuPb5P82Vad2M9+eOONDzW4tQABmzQocgwbGBiYeUBckFgCPg1AhR8/AEl5IGb8gV/lKBgFo2AUjFAAAKLwUCvPXM8bAAAAAElFTkSuQmCC","orcid":"","institution":"Jiangnan University","correspondingAuthor":true,"prefix":"","firstName":"Jun","middleName":"","lastName":"Kong","suffix":""},{"id":465791041,"identity":"62823825-dd4d-44ba-ac58-7ddd9b550778","order_by":2,"name":"Min Jiang","email":"","orcid":"","institution":"Jiangnan University","correspondingAuthor":false,"prefix":"","firstName":"Min","middleName":"","lastName":"Jiang","suffix":""},{"id":465791042,"identity":"e7afee66-029d-46fd-9d1d-1a7d68f46c37","order_by":3,"name":"Xuefeng Tao","email":"","orcid":"","institution":"Jiangnan University","correspondingAuthor":false,"prefix":"","firstName":"Xuefeng","middleName":"","lastName":"Tao","suffix":""}],"badges":[],"createdAt":"2025-05-12 12:38:19","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6646658/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6646658/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s13042-026-03057-w","type":"published","date":"2026-03-30T15:59:56+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":106344265,"identity":"c724213d-4348-41e1-8862-cf868022d0c1","added_by":"auto","created_at":"2026-04-07 16:13:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1053010,"visible":true,"origin":"","legend":"","description":"","filename":"MTADOReAD.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6646658/v1_covered_c825469a-cd63-44cb-b6ad-27bc3bc00de1.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multivariate Time Series Anomaly Detection for Over-reconstruction of Anomalous Data","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":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Unsupervised anomaly detection, over-reconstruction of anomalous data, gated diversity memory module (GDMM), pollution calibration strategy (PCS)","lastPublishedDoi":"10.21203/rs.3.rs-6646658/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6646658/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAnomaly detection in multivariate time series (MTS) data is vital for maintaining system stability and safety. Current reconstruction-based methods aim to learn the normal patterns of data. However, these methods often suffer from the model's over-generalization and the polluted training set, leading to the over-reconstruction of anomalous data. To address these issues, we propose MTAD-ORe, an unsupervised MTS Anomaly Detection framework for Over-Reconstruction of anomalous data. Firstly, to alleviate the model's over-generalization, we design the Gated Diversity Memory Module (GDMM) and the Cross Fusion Module (CFM). GDMM designs a memory block to store typical and diverse features of normal data, which is used for bidirectional updating with the input data. This makes the reconstructed results of anomalous data resemble normal data. Meanwhile, to prevent information loss during the bidirectional updates, CFM is designed to integrate feature information. Secondly, to calibrate the learning bias caused by the polluted training set, we design the Pollution Calibration Strategy (PCS). PCS creates a more reasonable objective for MTAD-ORe, which leads MTAD-ORe to concentrate more on plausible normal data. Experimental studies on four public datasets demonstrate that our MTAD-ORe outperforms several existing competitive baselines.\u003c/p\u003e","manuscriptTitle":"Multivariate Time Series Anomaly Detection for Over-reconstruction of Anomalous Data","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-04 03:44:10","doi":"10.21203/rs.3.rs-6646658/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-08-23T01:23:05+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-27T02:29:45+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-19T07:18:49+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-06-09T04:03:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"296465231397597628162841806041228725398","date":"2025-06-06T02:28:36+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"187277768539137739714443309499301746105","date":"2025-06-04T06:01:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"320633984743652643468820568446761014778","date":"2025-06-02T09:55:23+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-06-02T04:47:12+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-05-19T09:53:05+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-05-14T09:38:52+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Machine Learning and Cybernetics","date":"2025-05-12T12:26:27+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"4517b203-f4e7-4f66-8b39-08365255a84a","owner":[],"postedDate":"June 4th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-04-07T16:08:33+00:00","versionOfRecord":{"articleIdentity":"rs-6646658","link":"https://doi.org/10.1007/s13042-026-03057-w","journal":{"identity":"international-journal-of-machine-learning-and-cybernetics","isVorOnly":false,"title":"International Journal of Machine Learning and Cybernetics"},"publishedOn":"2026-03-30 15:59:56","publishedOnDateReadable":"March 30th, 2026"},"versionCreatedAt":"2025-06-04 03:44:10","video":"","vorDoi":"10.1007/s13042-026-03057-w","vorDoiUrl":"https://doi.org/10.1007/s13042-026-03057-w","workflowStages":[]},"version":"v1","identity":"rs-6646658","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6646658","identity":"rs-6646658","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}