Quxai: Explainers for Hybrid Quantum Machine Learning Models

Quxai: Explainers for Hybrid Quantum Machine Learning Models | 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 Quxai: Explainers for Hybrid Quantum Machine Learning Models Saikat Barua, Mostafizur Rahman, Shehenaz Khaled, Md Jafor Sadek, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6804209/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 The emergence of hybrid quantum-classical machine learning (HQML) models opens new horizons of computational intelligence but their fundamental complexity frequently leads to black box behavior that undermines transparency and reliability in their application. Although XAI for quantum systems still in its infancy, a major research gap is evident in robust global and local explainability approaches that are designed for HQML architectures that employ quantized feature encoding followed by classical learning. The gap is the focus of this work, which introduces QuXAI, an framework based upon Q-MEDLEY, an explainer for explaining feature importance in these hybrid systems. Our model entails the creation of HQML models incorporating quantum feature maps, the use of Q-MEDLEY, which combines feature based inferences, preserving the quantum transformation stage and visualizing the resulting attributions. Our result shows that Q-MEDLEY delineates influential classical aspects in HQML models, as well as separates their noise, and competes well against established XAI techniques in classical validation settings. Ablation studies more significantly expose the virtues of the composite structure used in Q-MEDLEY. The implications of this work are critically important, as it provides a route to improve the interpretability and reliability of HQML models, thus promoting greater confidence and being able to engage in safer and more responsible use of quantum-enhanced AI technology. Our code and experiments are open-sourced at: https://github.com/GitsSaikat/QuXAI Artificial Intelligence and Machine Learning Quantum Machine Learning Explainable AI Hybrid Quantum-Classical Algorithms Interpretable Quantum Systems Quantum Feature Engineering Trustworthy Quantum AI Full Text Additional Declarations The authors declare no competing interests. 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-6804209","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":465427919,"identity":"b4784799-0ea2-435a-a559-e27c3e17d781","order_by":0,"name":"Saikat Barua","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0003-0386-1263","institution":"North South University","correspondingAuthor":true,"prefix":"","firstName":"Saikat","middleName":"","lastName":"Barua","suffix":""},{"id":465427920,"identity":"d83a5f26-b8ce-4996-8baf-73005415b1fb","order_by":1,"name":"Mostafizur Rahman","email":"","orcid":"","institution":"North South University","correspondingAuthor":false,"prefix":"","firstName":"Mostafizur","middleName":"","lastName":"Rahman","suffix":""},{"id":465427921,"identity":"e884fc5d-4914-44c3-a0b9-fd0f16198a41","order_by":2,"name":"Shehenaz Khaled","email":"","orcid":"","institution":"North South University","correspondingAuthor":false,"prefix":"","firstName":"Shehenaz","middleName":"","lastName":"Khaled","suffix":""},{"id":465427922,"identity":"ff011b3c-a027-47f4-9f3a-5809da15c123","order_by":3,"name":"Md Jafor Sadek","email":"","orcid":"","institution":"North South University","correspondingAuthor":false,"prefix":"","firstName":"Md","middleName":"Jafor","lastName":"Sadek","suffix":""},{"id":465427923,"identity":"4bef95e5-0bac-41d6-8d53-46a980b3e0fd","order_by":4,"name":"Rafiul Islam","email":"","orcid":"","institution":"North South University","correspondingAuthor":false,"prefix":"","firstName":"Rafiul","middleName":"","lastName":"Islam","suffix":""},{"id":465427924,"identity":"513efb66-ddfd-4c2c-bdfd-be36cc1d1fe0","order_by":5,"name":"Dr. Shahnewaz Siddique","email":"","orcid":"","institution":"North South University","correspondingAuthor":false,"prefix":"Dr.","firstName":"Shahnewaz","middleName":"","lastName":"Siddique","suffix":""}],"badges":[],"createdAt":"2025-06-02 17:02:32","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6804209/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6804209/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":83819656,"identity":"4313f9bd-a1ca-41a9-98b6-db28a347a482","added_by":"auto","created_at":"2025-06-03 08:31:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":868057,"visible":true,"origin":"","legend":"","description":"","filename":"2505.10167v2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6804209/v1_covered_55972544-0159-4fed-af95-b6e5344afd1f.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eQuxai: Explainers for Hybrid Quantum Machine Learning Models\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"North South University","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":"Quantum Machine Learning, Explainable AI, Hybrid Quantum-Classical Algorithms, Interpretable Quantum Systems, Quantum Feature Engineering, Trustworthy Quantum AI","lastPublishedDoi":"10.21203/rs.3.rs-6804209/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6804209/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe emergence of hybrid quantum-classical machine learning (HQML) models opens new horizons of computational intelligence but their fundamental complexity frequently leads to black box behavior that undermines transparency and reliability in their application. Although XAI for quantum systems still in its infancy, a major research gap is evident in robust global and local explainability approaches that are designed for HQML architectures that employ quantized feature encoding followed by classical learning. The gap is the focus of this work, which introduces QuXAI, an framework based upon Q-MEDLEY, an explainer for explaining feature importance in these hybrid systems. Our model entails the creation of HQML models incorporating quantum feature maps, the use of Q-MEDLEY, which combines feature based inferences, preserving the quantum transformation stage and visualizing the resulting attributions. Our result shows that Q-MEDLEY delineates influential classical aspects in HQML models, as well as separates their noise, and competes well against established XAI techniques in classical validation settings. Ablation studies more significantly expose the virtues of the composite structure used in Q-MEDLEY. The implications of this work are critically important, as it provides a route to improve the interpretability and reliability of HQML models, thus promoting greater confidence and being able to engage in safer and more responsible use of quantum-enhanced AI technology.\u003c/p\u003e\n\u003cp\u003eOur code and experiments are open-sourced at: https://github.com/GitsSaikat/QuXAI\u003c/p\u003e","manuscriptTitle":"Quxai: Explainers for Hybrid Quantum Machine Learning Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-03 07:59:28","doi":"10.21203/rs.3.rs-6804209/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":"2cf85385-f8e3-4edd-b7f7-cbca89a4088e","owner":[],"postedDate":"June 3rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":49437639,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-06-03T07:59:28+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-03 07:59:28","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6804209","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6804209","identity":"rs-6804209","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}