A Reinforcement-Driven Multiple Instance Learning Framework for Multi-Task Speaker Attribute Prediction

A Reinforcement-Driven Multiple Instance Learning Framework for Multi-Task Speaker Attribute Prediction | 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 A Reinforcement-Driven Multiple Instance Learning Framework for Multi-Task Speaker Attribute Prediction Stijn Lakeman, Seyed Sahand Mohammadi Ziabari, Ali Mohammed Mansoor Alsahag This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7633867/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 Standard models for predicting speaker attributes from text often fail to manage multiple, interdependent attributes simultaneously, and existing Reinforced Multiple Instance Learning frameworks are typically limited to single-task prediction. To address this, we propose and evaluate a Reinforced, Multi-Task, Multiple Instance Learning framework, a novel framework that enhances Reinforced Multiple Instance Learning with Multi-Task Learning to predict a speaker’s age, gender, and political party from congressional speeches. A central goal of our work was to investigate the optimal parameter-sharing strategy. We compared a fully shared architecture against a dynamic task clustering mechanism designed to mitigate negative transfer by adaptively grouping related tasks. Our results demonstrate that the multi-task approach significantly outperforms single-task baselines. Interestingly, the model with a fully shared representation achieved the highest macro average F1-score of 0.668, suggesting the tasks in this dataset were sufficiently correlated to benefit from shared features without needing adaptive separation. This work contributes a more effective method for weakly-supervised, multi-attribute prediction and provides crucial insights into the trade-offs between different parameter-sharing strategies in Multi-Task Learning. Multi-Task Learning Multiple Instance Learning Reinforcement Learning Speaker Attribute Prediction Task Clustering Weakly Supervised Learning 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-7633867","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":516980087,"identity":"5dfe6d4d-7313-4b9e-9fd1-0103c6852a25","order_by":0,"name":"Stijn Lakeman","email":"","orcid":"","institution":"University of Amsterdam","correspondingAuthor":false,"prefix":"","firstName":"Stijn","middleName":"","lastName":"Lakeman","suffix":""},{"id":516980088,"identity":"582b8ecf-0faf-4df9-a93b-dd66c2ff58e8","order_by":1,"name":"Seyed Sahand Mohammadi Ziabari","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFElEQVRIie2RMUvEMBiGEwPeEnD9QKG/QEgRzgpX+ldSCrmlToLcJHXJLQducj+jLpXbWrKeulbqcEXofNNxww0mhZtspaNDnuGDN+The0MQslj+L3k7gSNAzMRtm0kyXCmWbcYDFDOMQugfipOMNifl7Mu5fFZ1uTl4zvXorVa+VA46f+xUWE4ZideNm1XiyuMU3NViytStVG5yUXQriCKiL+Cs4mPgADjNBdKKwAmEvcWMEmTVdAecQZB+NEjdSBH0KfrhzChhVsV6C4cwLfUWLCdhn8IUZSpeq0grdx7PIVotG1Qs3ieR7Cs2n9ff8Uz5utjL5/7w4L+eCbLd34P/BFHeWYwcP+UXp93HFovFYhnAD2ivaE95+bRUAAAAAElFTkSuQmCC","orcid":"","institution":"university of amsterdam","correspondingAuthor":true,"prefix":"","firstName":"Seyed","middleName":"Sahand Mohammadi","lastName":"Ziabari","suffix":""},{"id":516980089,"identity":"15f8ce99-8c03-4ad3-8caa-b22002eaebdd","order_by":2,"name":"Ali Mohammed Mansoor Alsahag","email":"","orcid":"","institution":"university of amsterdam","correspondingAuthor":false,"prefix":"","firstName":"Ali","middleName":"Mohammed Mansoor","lastName":"Alsahag","suffix":""}],"badges":[],"createdAt":"2025-09-16 21:34:06","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-7633867/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7633867/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91686586,"identity":"8b8f4486-66ca-437a-979a-b86946fa6783","added_by":"auto","created_at":"2025-09-19 07:52:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":530145,"visible":true,"origin":"","legend":"","description":"","filename":"StijnAReinforcementDrivenMultipleInstanceLearningMethodforMultiTaskSpeakerAttributePredictionSpringer.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7633867/v1_covered_cac1678f-ebc7-4253-9157-c441860f0701.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eA Reinforcement-Driven Multiple Instance Learning Framework for Multi-Task Speaker Attribute Prediction\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"University of Amsterdam","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":"Multi-Task Learning, Multiple Instance Learning, Reinforcement Learning, Speaker Attribute Prediction, Task Clustering, Weakly Supervised Learning ","lastPublishedDoi":"10.21203/rs.3.rs-7633867/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7633867/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eStandard models for predicting speaker attributes from text often fail to manage multiple, interdependent attributes simultaneously, and existing Reinforced Multiple Instance Learning frameworks are typically limited to single-task prediction. To address this, we propose and evaluate a Reinforced, Multi-Task, Multiple Instance Learning framework, a novel framework that enhances Reinforced Multiple Instance Learning with Multi-Task Learning to predict a speaker’s age, gender, and political party from congressional speeches. A central goal of our work was to investigate the optimal parameter-sharing strategy. We compared a fully shared architecture against a dynamic task clustering mechanism designed to mitigate negative transfer by adaptively grouping related tasks. Our results demonstrate that the multi-task approach significantly outperforms single-task baselines. Interestingly, the model with a fully shared representation achieved the highest macro average F1-score of 0.668, suggesting the tasks in this dataset were sufficiently correlated to benefit from shared features without needing adaptive separation. This work contributes a more effective method for weakly-supervised, multi-attribute prediction and provides crucial insights into the trade-offs between different parameter-sharing strategies in Multi-Task Learning.\u003c/p\u003e","manuscriptTitle":"A Reinforcement-Driven Multiple Instance Learning Framework for Multi-Task Speaker Attribute Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-19 07:43:55","doi":"10.21203/rs.3.rs-7633867/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":"856fc487-8fe1-48e4-bdc5-e6d076cbf2d1","owner":[],"postedDate":"September 19th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-09-19T07:43:55+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-19 07:43:55","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7633867","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7633867","identity":"rs-7633867","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}