Safe semi-supervised learning using a bayesian neural network
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Bae, Jinsoo | - |
dc.contributor.author | Lee, Minjung | - |
dc.contributor.author | Kim, Seoung Bum | - |
dc.date.accessioned | 2022-11-18T01:40:43Z | - |
dc.date.available | 2022-11-18T01:40:43Z | - |
dc.date.created | 2022-11-17 | - |
dc.date.issued | 2022-10 | - |
dc.identifier.issn | 0020-0255 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/145702 | - |
dc.description.abstract | Semi-supervised learning attempts to use a large set of unlabeled data to increase the pre-diction accuracy of machine learning models when the amount of labeled data is limited. However, in realistic cases, unlabeled data may worsen performance because they contain out-of-distribution (OOD) data that differ from the labeled data. To address this issue, safe semi-supervised deep learning has recently been presented. This study suggests a new safe semi-supervised algorithm that uses an uncertainty-aware Bayesian neural network. Our proposed method, safe uncertainty-based consistency training (SafeUC), uses Bayesian uncertainty to minimize the harmful effects caused by unlabeled OOD examples. The pro-posed method improves the model's generalization performance by regularizing the net-work for consistency against uncertain noise. Moreover, to avoid uncertain prediction results, the proposed method includes a practical inference tip based on a well -calibrated uncertainty. The effectiveness of the proposed method is demonstrated in the experimental results on CIFAR-10 and SVHN by showing that it achieved state-of-the-art performance for all semi-supervised learning tasks with OOD data presence rates.(c) 2022 Elsevier Inc. All rights reserved. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | ELSEVIER SCIENCE INC | - |
dc.title | Safe semi-supervised learning using a bayesian neural network | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Kim, Seoung Bum | - |
dc.identifier.doi | 10.1016/j.ins.2022.08.094 | - |
dc.identifier.scopusid | 2-s2.0-85137176178 | - |
dc.identifier.wosid | 000863219500003 | - |
dc.identifier.bibliographicCitation | INFORMATION SCIENCES, v.612, pp.453 - 464 | - |
dc.relation.isPartOf | INFORMATION SCIENCES | - |
dc.citation.title | INFORMATION SCIENCES | - |
dc.citation.volume | 612 | - |
dc.citation.startPage | 453 | - |
dc.citation.endPage | 464 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Information Systems | - |
dc.subject.keywordAuthor | Safe semi-supervised deep learning | - |
dc.subject.keywordAuthor | Out-of-distribution | - |
dc.subject.keywordAuthor | Bayesian neural network | - |
dc.subject.keywordAuthor | Uncertainty | - |
dc.subject.keywordAuthor | Uncertain noise | - |
dc.subject.keywordAuthor | Consistency regularization | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
145 Anam-ro, Seongbuk-gu, Seoul, 02841, Korea+82-2-3290-2963
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.