Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Counterfactual explanation based on gradual construction for deep networks

Authors
Jung, Hong-GyuKang, Sin-HanKim, Hee-DongWon, Dong-OkLee, Seong-Whan
Issue Date
12월-2022
Publisher
ELSEVIER SCI LTD
Keywords
Explainable AI; Counterfactual explanation; Interpretability; Model -agnostics; Generative model
Citation
PATTERN RECOGNITION, v.132
Indexed
SCIE
SCOPUS
Journal Title
PATTERN RECOGNITION
Volume
132
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/145622
DOI
10.1016/j.patcog.2022.108958
ISSN
0031-3203
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.
Files in This Item
There are no files associated with this item.
Appears in
Collections
Graduate School > Department of Artificial Intelligence > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Lee, Seong Whan photo

Lee, Seong Whan
인공지능학과
Read more

Altmetrics

Total Views & Downloads

BROWSE