Adaptive Adversarial Augmentation for Molecular Property Prediction

Adaptive Adversarial Augmentation for Molecular Property 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 Adaptive Adversarial Augmentation for Molecular Property Prediction Soyoung Cho, Sungchul Hong, Jong-June Jeon This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3990132/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 Graph Neural Networks (GNNs) exhibit potential in predicting the properties of molecules, but computational analyses with the GNNs often encounter the problem of data imbalance or overfitting. Augmentation techniques have emerged as a popular solution, and adversarial perturbation to node features achieves a significant improvement in enhancing the model's generalization capacity. Despite remarkable advancement, there is scarce research about systematically tuning the adversarial augmentation. We propose a new framework for an adversarial perturbation with influential graph features. Our method selects the data to apply adversarial augmentation based on the one-step influence function that measures the influence of each training sample on prediction in each iteration. In particular, the approximation of the one-step influence function has wide applicability to evaluate a model's validity on the observation level for a large-scale neural network. Selected data using the one-step influence function are likely to be located near the decision boundary, and experimental results demonstrated that augmentation of such data has improved the model's performance. Molecular Properties Prediction Influence Function Adversarial Augmentation Graph Neural Network Full Text Additional Declarations No competing interests reported. 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-3990132","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":274937699,"identity":"0b88212d-276e-4971-b8f4-cfefed7c82a6","order_by":0,"name":"Soyoung Cho","email":"","orcid":"","institution":"University of Seoul","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Soyoung","middleName":"","lastName":"Cho","suffix":""},{"id":274937700,"identity":"442f0742-4e79-4aff-acec-279adf2f397f","order_by":1,"name":"Sungchul Hong","email":"","orcid":"","institution":"University of Seoul","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Sungchul","middleName":"","lastName":"Hong","suffix":""},{"id":274937701,"identity":"bdc24b57-70fb-4497-8178-ee89f6dd6ab9","order_by":2,"name":"Jong-June Jeon","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAx0lEQVRIiWNgGAWjYBACxoYDDAZAWg4mYEC0FmPitcBAYgPRWpgbDzAUfKi4k77hePsDhh81DMbmDQS0gBxmOOPMs9wNZ84YMPYcYzCTOUCEFmPetsO5G27kMDDwNjDYSBByGFjL37bD6QY30h8w/iVaC2Pb4QSDGwkGzEBbzIjQcrDBsOfMYcOZQL8cljkmYUxQi+GMw8cMflQcluc73v7w4ZsaG8MZhLUcbINHxQEGBoJ2MDDI8zcwPyCsbBSMglEwCkY0AADF2ULY2N/lYgAAAABJRU5ErkJggg==","orcid":"","institution":"University of Seoul","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Jong-June","middleName":"","lastName":"Jeon","suffix":""}],"badges":[],"createdAt":"2024-02-26 06:15:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3990132/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3990132/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":52938175,"identity":"325f4cef-0716-47cf-a895-c8083bcdbc3a","added_by":"auto","created_at":"2024-03-18 23:37:54","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1617251,"visible":true,"origin":"","legend":"","description":"","filename":"MolecularPropertyPrediction.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3990132/v1_covered_9285bcfd-41a9-4923-8b5b-085dfba1e16c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Adaptive Adversarial Augmentation for Molecular Property Prediction","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":"Molecular Properties Prediction, Influence Function, Adversarial Augmentation, Graph Neural Network","lastPublishedDoi":"10.21203/rs.3.rs-3990132/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3990132/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eGraph Neural Networks (GNNs) exhibit potential in predicting the properties of molecules, but computational analyses with the GNNs often encounter the problem of data imbalance or overfitting. Augmentation techniques have emerged as a popular solution, and adversarial perturbation to node features achieves a significant improvement in enhancing the model's generalization capacity. Despite remarkable advancement, there is scarce research about systematically tuning the adversarial augmentation. We propose a new framework for an adversarial perturbation with influential graph features. Our method selects the data to apply adversarial augmentation based on the one-step influence function that measures the influence of each training sample on prediction in each iteration. In particular, the approximation of the one-step influence function has wide applicability to evaluate a model's validity on the observation level for a large-scale neural network. Selected data using the one-step influence function are likely to be located near the decision boundary, and experimental results demonstrated that augmentation of such data has improved the model's performance. \u003c/p\u003e","manuscriptTitle":"Adaptive Adversarial Augmentation for Molecular Property Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-02-28 02:46:56","doi":"10.21203/rs.3.rs-3990132/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":"e93bae1f-764a-45b8-a067-e4042f141fd5","owner":[],"postedDate":"February 28th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-03-18T23:29:35+00:00","versionOfRecord":[],"versionCreatedAt":"2024-02-28 02:46:56","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3990132","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3990132","identity":"rs-3990132","version":["v1"]},"buildId":"7rjqhiLT3MXkJMwkYKINL","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}