Counterfactual explanation based on gradual construction for deep networks
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jung, Hong-Gyu | - |
dc.contributor.author | Kang, Sin-Han | - |
dc.contributor.author | Kim, Hee-Dong | - |
dc.contributor.author | Won, Dong-Ok | - |
dc.contributor.author | Lee, Seong-Whan | - |
dc.date.accessioned | 2022-11-17T09:40:49Z | - |
dc.date.available | 2022-11-17T09:40:49Z | - |
dc.date.created | 2022-11-17 | - |
dc.date.issued | 2022-12 | - |
dc.identifier.issn | 0031-3203 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/145622 | - |
dc.description.abstract | To understand the black-box characteristics of deep networks, counterfactual explanation that deduces not only the important features of an input space but also how those features should be modified to classify input as a target class has gained an increasing interest. The patterns that deep networks have learned from a training dataset can be grasped by observing the feature variation among various classes. However, current approaches perform the feature modification to increase the classification probability for the target class irrespective of the internal characteristics of deep networks. This often leads to un-clear explanations that deviate from real-world data distributions. To address this problem, we propose a counterfactual explanation method that exploits the statistics learned from a training dataset. Especially, we gradually construct an explanation by iterating over masking and composition steps. The masking step aims to select an important feature from the input data to be classified as a target class. Mean-while, the composition step aims to optimize the previously selected feature by ensuring that its output score is close to the logit space of the training data that are classified as the target class. Experimental results show that our method produces human-friendly interpretations on various classification datasets and verify that such interpretations can be achieved with fewer feature modification.(c) 2022 Elsevier Ltd. All rights reserved. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | ELSEVIER SCI LTD | - |
dc.subject | CLASSIFICATION | - |
dc.title | Counterfactual explanation based on gradual construction for deep networks | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Lee, Seong-Whan | - |
dc.identifier.doi | 10.1016/j.patcog.2022.108958 | - |
dc.identifier.scopusid | 2-s2.0-85135958834 | - |
dc.identifier.wosid | 000860613700003 | - |
dc.identifier.bibliographicCitation | PATTERN RECOGNITION, v.132 | - |
dc.relation.isPartOf | PATTERN RECOGNITION | - |
dc.citation.title | PATTERN RECOGNITION | - |
dc.citation.volume | 132 | - |
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.journalResearchArea | Engineering | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Engineering, Electrical & Electronic | - |
dc.subject.keywordPlus | CLASSIFICATION | - |
dc.subject.keywordAuthor | Explainable AI | - |
dc.subject.keywordAuthor | Counterfactual explanation | - |
dc.subject.keywordAuthor | Interpretability | - |
dc.subject.keywordAuthor | Model -agnostics | - |
dc.subject.keywordAuthor | Generative model | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
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.