Perturbing the Gradient for alleviating Meta Overfitting

Perturbing the Gradient for alleviating Meta Overfitting | 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 Perturbing the Gradient for alleviating Meta Overfitting Manas Gogoi, Sambhavi Tiwari, Shekhar Verma This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4659990/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 reason for Meta Overfitting can be attributed to two factors: Mutual Non-exclusivity and the Lack of diversity, consequent to which a single global function can fit the support set data of all the meta-training tasks and fail to generalize to new unseen tasks. This issue is evidenced by low error rates on the meta-training tasks, but high error rates on new tasks. However, there can be a number of novel solutions to this problem keeping in mind any of the two objectives to be attained, i.e. to increase diversity in the tasks and to reduce the confidence of the model for some of the tasks. Inlight of the above, this paper proposes a number of solutions to tackle meta-overfitting on few-shot learning settings, such as few-shot sinusoid regression and few shot classification. Our proposed approaches demonstrate improved generalization performance compared to state-of-the-art baselines for learning in a non-mutually exclusive task setting. Overall, this paper aims to provide insights into tackling overfitting in meta-learning and to advance the field towards more robust and generalizable models. Meta Overfitting Optimization Meta Learning MAML 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-4659990","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":323559168,"identity":"4ed39b2f-3ae2-4398-8ff2-c2838ece5427","order_by":0,"name":"Manas Gogoi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA30lEQVRIiWNgGAWjYBADZsb2BiBlYEG8FnbmngMgLRLEa+Fnn5EAoonQott+9uDHH79qpXlnPr+64UeBBAN/e3cCXi1mZ/KSpXn7jhtLzs4pu9kDdJjEmbMb8Gs5kGMgzdhzLNlwdk7aDR6gFgOJXAJazr8x/vmz51j9/ptn0m7+IUrLjRwzCZ4fNcyMM9iP3SbOlhtvzKx5Gw4wM/bksN2WMZDgIeyX8znGN3/8qQNG5fFnN9/8sZHjb+/FrwUMGNsOA0keAxCbh7ByMPhTByTYHxCpehSMglEwCkYaAADEV0ynvgZJ5AAAAABJRU5ErkJggg==","orcid":"","institution":"Indian Institute of Information Technology, Allahabad","correspondingAuthor":true,"prefix":"","firstName":"Manas","middleName":"","lastName":"Gogoi","suffix":""},{"id":323559169,"identity":"4eacc1bd-0654-4a58-87b4-e33f6782f02d","order_by":1,"name":"Sambhavi Tiwari","email":"","orcid":"","institution":"Indian Institute of Information Technology, Allahabad","correspondingAuthor":false,"prefix":"","firstName":"Sambhavi","middleName":"","lastName":"Tiwari","suffix":""},{"id":323559173,"identity":"99bf3797-72b8-4210-aef3-4b5b7eee59e6","order_by":2,"name":"Shekhar Verma","email":"","orcid":"","institution":"Indian Institute of Information Technology, Allahabad","correspondingAuthor":false,"prefix":"","firstName":"Shekhar","middleName":"","lastName":"Verma","suffix":""}],"badges":[],"createdAt":"2024-06-29 15:39:41","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4659990/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4659990/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":67433836,"identity":"aeca5ed3-263d-4c36-8fcb-fce295537f15","added_by":"auto","created_at":"2024-10-25 03:01:50","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":450186,"visible":true,"origin":"","legend":"","description":"","filename":"ImageandVideoProcessing.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4659990/v1_covered_78e599d7-0aae-49b9-bf1f-1ac7c2bca506.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Perturbing the Gradient for alleviating Meta Overfitting","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":"Meta Overfitting, Optimization, Meta Learning, MAML","lastPublishedDoi":"10.21203/rs.3.rs-4659990/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4659990/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The reason for Meta Overfitting can be attributed to two factors: Mutual Non-exclusivity and the Lack of diversity, consequent to which a single global function can fit the support set data of all the meta-training tasks and fail to generalize to new unseen tasks. This issue is evidenced by low error rates on the meta-training tasks, but high error rates on new tasks. However, there can be a number of novel solutions to this problem keeping in mind any of the two objectives to be attained, i.e. to increase diversity in the tasks and to reduce the confidence of the model for some of the tasks. Inlight of the above, this paper proposes a number of solutions to tackle meta-overfitting on few-shot learning settings, such as few-shot sinusoid regression and few shot classification. Our proposed approaches demonstrate improved generalization performance compared to state-of-the-art baselines for learning in a non-mutually exclusive task setting. Overall, this paper aims to provide insights into tackling overfitting in meta-learning and to advance the field towards more robust and generalizable models.","manuscriptTitle":"Perturbing the Gradient for alleviating Meta Overfitting","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-23 13:55:22","doi":"10.21203/rs.3.rs-4659990/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":"c7e231ed-526a-4350-baa2-b558c9a46e7c","owner":[],"postedDate":"July 23rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-10-25T02:53:43+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-23 13:55:22","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4659990","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4659990","identity":"rs-4659990","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}