Specific-Input LIME Explanations for Tabular Data Based on Deep Learning Modelsopen access
- Authors
- An, Junkang; Zhang, Yiwan; Joe, Inwhee
- Issue Date
- Aug-2023
- Publisher
- MDPI
- Keywords
- explainable AI; interpretability; machine learning; tabular data
- Citation
- APPLIED SCIENCES-BASEL, v.13, no.15, pp.1 - 19
- Indexed
- SCIE
SCOPUS
- Journal Title
- APPLIED SCIENCES-BASEL
- Volume
- 13
- Number
- 15
- Start Page
- 1
- End Page
- 19
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/189627
- DOI
- 10.3390/app13158782
- 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.
- Files in This Item
-
- Appears in
Collections - 서울 공과대학 > 서울 컴퓨터소프트웨어학부 > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.