Optimizing Learning Across Multimodal Transfer Features for Modelling Olfactory Perception

Optimizing Learning Across Multimodal Transfer Features for Modelling Olfactory Perception | 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 Article Optimizing Learning Across Multimodal Transfer Features for Modelling Olfactory Perception Daniel Shin, Gao Pei, Priyadarshini Kumari, Tarek R. Besold This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3607229/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 For humans and other animals, the sense of smell provides crucial information in many situations of everyday life. Still, the study of olfactory perception has received only limited attention outside of the biological sciences. From an AI perspective, the complexity of the interactions between olfactory receptors and volatile molecules and the scarcity of comprehensive olfactory datasets present unique challenges in this sensory domain. Previous works have explored the relationship between molecular structure and odor descriptors using fully supervised training approaches. However, these methods are data-intensive and poorly generalized due to labeled data scarcity, particularly for rare-class samples. Our study partially tackles the challenges of data scarcity and label skewness through multimodal transfer learning. We investigate the potential of large molecular foundation models trained on extensive unlabeled molecular data to effectively model olfactory perception. Additionally, we explore the integration of different molecular representations, including molecular graphs and text-based SMILES encodings, to achieve data efficiency and generalization of the learned model, particularly on sparsely represented classes. By leveraging complementary representations, we aim to learn robust perceptual features of odorants. However, we observe that traditional methods of combining modalities do not yield substantial gains in high-dimensional skewed label spaces. To address this challenge, we introduce a novel \emph{label-balancer} technique specifically designed for high-dimensional multi-label and multi-modal training. The label-balancer technique distributes learning objectives across modalities to optimize collaboratively for distinct subsets of labels. Our results suggest that multi-modal transfer features learned using the label-balancer technique are more effective and robust, surpassing the capabilities of traditional uni- or multi-modal approaches, particularly on rare-class samples. Physical sciences/Mathematics and computing/Computational science Physical sciences/Mathematics and computing/Computer science Full Text Additional Declarations No competing interests reported. Supplementary Files supplementaryfile.pdf 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-3607229","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":285973966,"identity":"0ecdccd8-fe54-499c-9957-4e8ad3c81fbb","order_by":0,"name":"Daniel Shin","email":"","orcid":"","institution":"Stanford University","correspondingAuthor":false,"prefix":"","firstName":"Daniel","middleName":"","lastName":"Shin","suffix":""},{"id":285973967,"identity":"8ba939c6-4100-4ae1-8eae-03f3080e96dc","order_by":1,"name":"Gao Pei","email":"","orcid":"","institution":"Nara Institute of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Gao","middleName":"","lastName":"Pei","suffix":""},{"id":285973968,"identity":"8ac1a070-9106-4a58-bbcd-7b7007cae617","order_by":2,"name":"Priyadarshini Kumari","email":"data:image/png;base64,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","orcid":"","institution":"Sony AI","correspondingAuthor":true,"prefix":"","firstName":"Priyadarshini","middleName":"","lastName":"Kumari","suffix":""},{"id":285973969,"identity":"47f13115-ad0e-4d6c-90ce-ef965449ed54","order_by":3,"name":"Tarek R. Besold","email":"","orcid":"","institution":"Sony AI","correspondingAuthor":false,"prefix":"","firstName":"Tarek","middleName":"R.","lastName":"Besold","suffix":""}],"badges":[],"createdAt":"2023-11-13 22:59:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3607229/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3607229/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":65930265,"identity":"19bc07bd-42ec-40e7-96de-71bd4a0d5948","added_by":"auto","created_at":"2024-10-04 13:48:03","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1118417,"visible":true,"origin":"","legend":"","description":"","filename":"NSROlfactoryMultimodalPerception.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3607229/v1_covered_26d3b2da-8621-4441-b8bb-64e3a8552dc2.pdf"},{"id":53957665,"identity":"cca0e2d8-7cc0-4841-9b50-729053536445","added_by":"auto","created_at":"2024-04-02 17:40:54","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":258502,"visible":true,"origin":"","legend":"","description":"","filename":"supplementaryfile.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3607229/v1/9c3fada8e311997d4009a976.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Optimizing Learning Across Multimodal Transfer Features for Modelling Olfactory Perception","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":"","lastPublishedDoi":"10.21203/rs.3.rs-3607229/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3607229/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"For humans and other animals, the sense of smell provides crucial information in many situations of everyday life. Still, the study of olfactory perception has received only limited attention outside of the biological sciences. From an AI perspective, the complexity of the interactions between olfactory receptors and volatile molecules and the scarcity of comprehensive olfactory datasets present unique challenges in this sensory domain. Previous works have explored the relationship between molecular structure and odor descriptors using fully supervised training approaches. However, these methods are data-intensive and poorly generalized due to labeled data scarcity, particularly for rare-class samples.\nOur study partially tackles the challenges of data scarcity and label skewness through multimodal transfer learning. We investigate the potential of large molecular foundation models trained on extensive unlabeled molecular data to effectively model olfactory perception. Additionally, we explore the integration of different molecular representations, including molecular graphs and text-based SMILES encodings, to achieve data efficiency and generalization of the learned model, particularly on sparsely represented classes. By leveraging complementary representations, we aim to learn robust perceptual features of odorants. However, we observe that traditional methods of combining modalities do not yield substantial gains in high-dimensional skewed label spaces. To address this challenge, we introduce a novel \\emph{label-balancer} technique specifically designed for high-dimensional multi-label and multi-modal training. The label-balancer technique distributes learning objectives across modalities to optimize collaboratively for distinct subsets of labels. Our results suggest that multi-modal transfer features learned using the label-balancer technique are more effective and robust, surpassing the capabilities of traditional uni- or multi-modal approaches, particularly on rare-class samples.","manuscriptTitle":"Optimizing Learning Across Multimodal Transfer Features for Modelling Olfactory Perception","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-02 17:40:42","doi":"10.21203/rs.3.rs-3607229/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":"0a5f0336-b0a8-4609-aaa2-99a6682e6348","owner":[],"postedDate":"April 2nd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":30097657,"name":"Physical sciences/Mathematics and computing/Computational science"},{"id":30097658,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2024-10-04T13:39:37+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-02 17:40:42","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3607229","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3607229","identity":"rs-3607229","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}