Specific-Input LIME Explanations for Tabular Data Based on Deep Learning Models
DC Field | Value | Language |
---|---|---|
dc.contributor.author | An, Junkang | - |
dc.contributor.author | Zhang, Yiwan | - |
dc.contributor.author | Joe, Inwhee | - |
dc.date.accessioned | 2023-09-04T07:03:27Z | - |
dc.date.available | 2023-09-04T07:03:27Z | - |
dc.date.created | 2023-08-29 | - |
dc.date.issued | 2023-08 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/189627 | - |
dc.description.abstract | Deep learning researchers believe that as deep learning models evolve, they can perform well on many tasks. However, the complex parameters of deep learning models make it difficult for users to understand how deep learning models make predictions. In this paper, we propose the specific-input local interpretable model-agnostic explanations (LIME) model, a novel interpretable artificial intelligence (XAI) method that interprets deep learning models of tabular data. The specific-input process uses feature importance and partial dependency plots (PDPs) to select the "what" and "how". In our experiments, we first obtain a basic interpretation of the data by simulating user behaviour. Second, we use our approach to understand "which" features deep learning models focus on and how these features affect the model's predictions. From the experimental results, we find that this approach improves the stability of LIME interpretations, compensates for the problem of LIME only focusing on local interpretations, and achieves a balance between global and local interpretations. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | MDPI | - |
dc.title | Specific-Input LIME Explanations for Tabular Data Based on Deep Learning Models | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Joe, Inwhee | - |
dc.identifier.doi | 10.3390/app13158782 | - |
dc.identifier.scopusid | 2-s2.0-85167927915 | - |
dc.identifier.wosid | 001045424600001 | - |
dc.identifier.bibliographicCitation | APPLIED SCIENCES-BASEL, v.13, no.15, pp.1 - 19 | - |
dc.relation.isPartOf | APPLIED SCIENCES-BASEL | - |
dc.citation.title | APPLIED SCIENCES-BASEL | - |
dc.citation.volume | 13 | - |
dc.citation.number | 15 | - |
dc.citation.startPage | 1 | - |
dc.citation.endPage | 19 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.isOpenAccess | Y | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Chemistry | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Materials Science | - |
dc.relation.journalResearchArea | Physics | - |
dc.relation.journalWebOfScienceCategory | Chemistry, Multidisciplinary | - |
dc.relation.journalWebOfScienceCategory | Engineering, Multidisciplinary | - |
dc.relation.journalWebOfScienceCategory | Materials Science, Multidisciplinary | - |
dc.relation.journalWebOfScienceCategory | Physics, Applied | - |
dc.subject.keywordAuthor | explainable AI | - |
dc.subject.keywordAuthor | interpretability | - |
dc.subject.keywordAuthor | machine learning | - |
dc.subject.keywordAuthor | tabular data | - |
dc.identifier.url | https://www.mdpi.com/2076-3417/13/15/8782 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
222, Wangsimni-ro, Seongdong-gu, Seoul, 04763, Korea+82-2-2220-1365
COPYRIGHT © 2021 HANYANG UNIVERSITY.
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.