Mneme: A Parallel Preprocessing Framework for Large Tabular Datasets

Mneme: A Parallel Preprocessing Framework for Large Tabular Datasets | 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 Mneme: A Parallel Preprocessing Framework for Large Tabular Datasets Argiris Sofotasios, Dimitris Metaxakis, Panagiotis Hadjidoukas This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7692811/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract The rapid expansion of Machine Learning (ML) applications, especially within its subfield of Deep Learning (DL), has created an increasing demand for efficient preprocessing of large tabular datasets that surpass the available memory capacity of single-node systems. This paper introduces a parallel framework, developed as a Python library, designed to efficiently preprocess large-scale tabular datasets for training Deep Neural Networks (DNNs). The library supports various data transformations, including normalization, categorical encoding, and missing value imputation, leveraging parallel computing and chunk-based processing to efficiently handle massive datasets. By distributing preprocessing tasks across multiple cores and facilitating the parallel loading and processing of data chunks without altering the original data file, the proposed library significantly reduces the time required for data preparation, which often represents a critical bottleneck in modern ML pipelines. Experimental evaluation demonstrates substantial performance gains over conventional sequential approaches and state-of-the-art (SOTA) solutions.Furthermore, the library integrates seamlessly with widely adopted DL frameworks, providing a scalable and flexible High-Performance Computing (HPC) tool for data preprocessing in contemporary ML workflows. Parallel Processing Data Preprocessing Large Tabular Datasets Machine Learning HPC Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 24 Feb, 2026 Reviews received at journal 07 Feb, 2026 Reviewers agreed at journal 04 Feb, 2026 Reviews received at journal 30 Jan, 2026 Reviewers agreed at journal 16 Jan, 2026 Reviewers agreed at journal 07 Nov, 2025 Reviewers agreed at journal 31 Oct, 2025 Reviewers invited by journal 29 Oct, 2025 Editor assigned by journal 28 Oct, 2025 Submission checks completed at journal 26 Sep, 2025 First submitted to journal 23 Sep, 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-7692811","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":541855044,"identity":"74a17687-f938-4c25-a550-4a267c568fa3","order_by":0,"name":"Argiris Sofotasios","email":"","orcid":"","institution":"University of Patras","correspondingAuthor":false,"prefix":"","firstName":"Argiris","middleName":"","lastName":"Sofotasios","suffix":""},{"id":541855045,"identity":"ffae603e-0140-4d19-9c21-cd6e9cb6fb52","order_by":1,"name":"Dimitris Metaxakis","email":"","orcid":"","institution":"University of Patras","correspondingAuthor":false,"prefix":"","firstName":"Dimitris","middleName":"","lastName":"Metaxakis","suffix":""},{"id":541855047,"identity":"6d6f9df4-d1c7-40c8-b691-1d2c45c1afcf","order_by":2,"name":"Panagiotis Hadjidoukas","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4klEQVRIiWNgGAWjYDACCSCSMGBm4Cddi2QDkHOAaC0MDMwMBgeI1WIu3fzwhkWBtZzxjdyDnz/usbNn4F/7AK8WyznHjC0kDNKNzW7kJUsceJac2CDx3ACvFoMbCWZAvxxO3HYjx0DiwAHmBAaJY/gdZnAj/RtYy+YZOcY/DhyotydCSw7Elg0SQMaBA4cZG/jb8GuxnJFTDPaLxJl3aRZnDhxPbJNgw6/FXCJ9422JP9Zy/O25h29UHKi25+cn5DAgZpYAM3kgImwSCYS1MH5A1sLAfwC/llEwCkbBKBhxAABos0ZWM8AKUgAAAABJRU5ErkJggg==","orcid":"","institution":"University of Patras","correspondingAuthor":true,"prefix":"","firstName":"Panagiotis","middleName":"","lastName":"Hadjidoukas","suffix":""}],"badges":[],"createdAt":"2025-09-23 09:53:39","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7692811/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7692811/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95542120,"identity":"a98ee165-e2aa-4a28-a4ab-7185e8910ffd","added_by":"auto","created_at":"2025-11-10 11:46:40","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5183,"visible":true,"origin":"","legend":"","description":"","filename":"c9bac7985a69414fa62d8512818110a8.json","url":"https://assets-eu.researchsquare.com/files/rs-7692811/v1/c4fc4e293a1d5ab5871b1f41.json"},{"id":95654449,"identity":"57d693ec-39e3-46f8-9ea3-4619cfe08757","added_by":"auto","created_at":"2025-11-11 16:11:59","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":93661,"visible":true,"origin":"","legend":"","description":"","filename":"c9bac7985a69414fa62d8512818110a81enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7692811/v1/a5175442ad525a5f9f467439.xml"},{"id":95542119,"identity":"8d196b74-ca3b-4004-b06c-66ffcbd3a4ae","added_by":"auto","created_at":"2025-11-10 11:46:40","extension":"eps","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40255,"visible":true,"origin":"","legend":"","description":"","filename":"Fig4.eps","url":"https://assets-eu.researchsquare.com/files/rs-7692811/v1/34a31fa40e05726252620e3d.eps"},{"id":95542121,"identity":"ecf26726-24d1-45d1-8188-a981b01918b3","added_by":"auto","created_at":"2025-11-10 11:46:40","extension":"eps","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":28651,"visible":true,"origin":"","legend":"","description":"","filename":"Fig6.eps","url":"https://assets-eu.researchsquare.com/files/rs-7692811/v1/db2b38d9a0d7fc61440df6d5.eps"},{"id":95542122,"identity":"f5a0dddb-2804-4b46-b650-7594fc1d0bc8","added_by":"auto","created_at":"2025-11-10 11:46:40","extension":"pdf","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1150369,"visible":true,"origin":"","legend":"","description":"","filename":"Mneme.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7692811/v1/e5ebf4ce6e55621b59f1e4ba.pdf"},{"id":95654460,"identity":"e892d9ab-0c02-487a-857c-2bce7cfb1fa4","added_by":"auto","created_at":"2025-11-11 16:12:03","extension":"pdf","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":399286,"visible":true,"origin":"","legend":"","description":"","filename":"coverletter.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7692811/v1/adc0e890cb65f0c79715867f.pdf"},{"id":95542123,"identity":"d9f64f19-1a7e-4f3d-ab8d-1f6f6147b8e5","added_by":"auto","created_at":"2025-11-10 11:46:40","extension":"py","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":631,"visible":true,"origin":"","legend":"","description":"","filename":"exampleAPI.py","url":"https://assets-eu.researchsquare.com/files/rs-7692811/v1/b7f9d25b65220e32bdf64331.py"},{"id":95542129,"identity":"70b73e1b-43b1-4a96-92c2-10b57d7b4f39","added_by":"auto","created_at":"2025-11-10 11:46:40","extension":"pdf","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1150379,"visible":true,"origin":"","legend":"","description":"","filename":"paper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7692811/v1/1f06cf21f33cbabdb0fd0a23.pdf"},{"id":95542124,"identity":"08033e66-fb74-44f5-9bb2-63e64c7fb7bd","added_by":"auto","created_at":"2025-11-10 11:46:40","extension":"cls","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55857,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-7692811/v1/095306a7b7f60934b2dcdeb7.cls"},{"id":95542128,"identity":"64ddb2bd-6b38-4768-8196-e70d302e0c16","added_by":"auto","created_at":"2025-11-10 11:46:40","extension":"bst","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64166,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7692811/v1/8be1c264f30bbeccda0342d2.bst"},{"id":95542126,"identity":"ed86a166-349c-4ed5-a63d-1fe7a34dfbda","added_by":"auto","created_at":"2025-11-10 11:46:40","extension":"xml","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":98582,"visible":true,"origin":"","legend":"","description":"","filename":"c9bac7985a69414fa62d8512818110a81structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7692811/v1/a3e8a9c66c901d1751efa657.xml"},{"id":95542130,"identity":"472e3e7b-cbf3-4bdd-93d9-24823145f487","added_by":"auto","created_at":"2025-11-10 11:46:40","extension":"html","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":107321,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7692811/v1/9c4f210410982870ee7864ac.html"},{"id":95659859,"identity":"63e1cf98-80e7-41e5-8fd6-90f14c435cd9","added_by":"auto","created_at":"2025-11-11 16:29:42","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1131342,"visible":true,"origin":"","legend":"","description":"","filename":"Mneme.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7692811/v1_covered_cf7a31a2-238a-4088-970a-73b7ede06615.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Mneme: A Parallel Preprocessing Framework for Large Tabular Datasets","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-parallel-programming","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ijpp","sideBox":"Learn more about [International Journal of Parallel Programming](http://link.springer.com/journal/10766)","snPcode":"10766","submissionUrl":"https://submission.nature.com/new-submission/10766/3","title":"International Journal of Parallel Programming","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Parallel Processing, Data Preprocessing, Large Tabular Datasets, Machine Learning, HPC","lastPublishedDoi":"10.21203/rs.3.rs-7692811/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7692811/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe rapid expansion of Machine Learning (ML) applications, especially within its subfield of Deep Learning (DL), has created an increasing demand for efficient preprocessing of large tabular datasets that surpass the available memory capacity of single-node systems. This paper introduces a parallel framework, developed as a Python library, designed to efficiently preprocess large-scale tabular datasets for training Deep Neural Networks (DNNs). The library supports various data transformations, including normalization, categorical encoding, and missing value imputation, leveraging parallel computing and chunk-based processing to efficiently handle massive datasets. By distributing preprocessing tasks across multiple cores and facilitating the parallel loading and processing of data chunks without altering the original data file, the proposed library significantly reduces the time required for data preparation, which often represents a critical bottleneck in modern ML pipelines. Experimental evaluation demonstrates substantial performance gains over conventional sequential approaches and state-of-the-art (SOTA) solutions.Furthermore, the library integrates seamlessly with widely adopted DL frameworks, providing a scalable and flexible High-Performance Computing (HPC) tool for data preprocessing in contemporary ML workflows.\u003c/p\u003e","manuscriptTitle":"Mneme: A Parallel Preprocessing Framework for Large Tabular Datasets","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-10 11:46:35","doi":"10.21203/rs.3.rs-7692811/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-02-24T05:15:54+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-07T07:58:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"77757899635837268143741954624915859290","date":"2026-02-04T13:07:37+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-30T12:17:20+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"275223869792509314200631202508278876786","date":"2026-01-16T18:29:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"300927000765175615220803511375891731926","date":"2025-11-07T14:05:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"287591843389468410340028947735931228762","date":"2025-10-31T11:32:31+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-29T07:22:09+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-28T09:11:55+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-26T11:20:34+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Parallel Programming","date":"2025-09-23T09:46:39+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-parallel-programming","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ijpp","sideBox":"Learn more about [International Journal of Parallel Programming](http://link.springer.com/journal/10766)","snPcode":"10766","submissionUrl":"https://submission.nature.com/new-submission/10766/3","title":"International Journal of Parallel Programming","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"8ca204f9-8f5a-45b7-ae83-fd841f3217d0","owner":[],"postedDate":"November 10th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-04T16:08:35+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-10 11:46:35","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7692811","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7692811","identity":"rs-7692811","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}