TY - GEN
T1 - Counterfactual Explanation for Regression via Disentanglement in Latent Space
AU - Zhao, Xuan
AU - Broelemann, Klaus
AU - Kasneci, Gjergji
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Counterfactual Explanations (CEs) help address the question: How can the factors that influence the prediction of a predictive model be changed to achieve a more favorable outcome from a user's perspective? Thus, they bear the potential to guide the user's interaction with AI systems since they represent easy-to-understand explanations. To be applicable, CEs need to be realistic and actionable. In the literature, various methods have been proposed to generate CEs. However, the majority of research on CEs focuses on classification problems where questions like "What should I do to get my rejected loan approved?"are raised. In practice, answering questions like "What should I do to increase my salary?"are of a more regressive nature. In this paper, we introduce a novel method to generate CEs for a pre-trained regressor by first disentangling the label-relevant from the label-irrelevant dimensions in the latent space. CEs are then generated by combining the label-irrelevant dimensions and the predefined output. The intuition behind this approach is that the ideal counterfactual search should focus on the label-irrelevant characteristics of the input and suggest changes toward target-relevant characteristics. Searching in the latent space could help achieve this goal. We show that our method maintains the characteristics of the query sample during the counterfactual search. In various experiments, we demonstrate that the proposed method is competitive based on different quality measures on image and tabular datasets in regression problem settings. It efficiently returns results closer to the original data manifold compared to three state-of-the-art methods, which is essential for realistic high-dimensional machine learning applications. Our code will be made available as an open-source package upon the publication of this work.
AB - Counterfactual Explanations (CEs) help address the question: How can the factors that influence the prediction of a predictive model be changed to achieve a more favorable outcome from a user's perspective? Thus, they bear the potential to guide the user's interaction with AI systems since they represent easy-to-understand explanations. To be applicable, CEs need to be realistic and actionable. In the literature, various methods have been proposed to generate CEs. However, the majority of research on CEs focuses on classification problems where questions like "What should I do to get my rejected loan approved?"are raised. In practice, answering questions like "What should I do to increase my salary?"are of a more regressive nature. In this paper, we introduce a novel method to generate CEs for a pre-trained regressor by first disentangling the label-relevant from the label-irrelevant dimensions in the latent space. CEs are then generated by combining the label-irrelevant dimensions and the predefined output. The intuition behind this approach is that the ideal counterfactual search should focus on the label-irrelevant characteristics of the input and suggest changes toward target-relevant characteristics. Searching in the latent space could help achieve this goal. We show that our method maintains the characteristics of the query sample during the counterfactual search. In various experiments, we demonstrate that the proposed method is competitive based on different quality measures on image and tabular datasets in regression problem settings. It efficiently returns results closer to the original data manifold compared to three state-of-the-art methods, which is essential for realistic high-dimensional machine learning applications. Our code will be made available as an open-source package upon the publication of this work.
KW - Counterfactual Explaination
KW - Regression
KW - XAI
UR - http://www.scopus.com/inward/record.url?scp=85186140893&partnerID=8YFLogxK
U2 - 10.1109/ICDMW60847.2023.00130
DO - 10.1109/ICDMW60847.2023.00130
M3 - Conference contribution
AN - SCOPUS:85186140893
T3 - IEEE International Conference on Data Mining Workshops, ICDMW
SP - 976
EP - 984
BT - Proceedings - 23rd IEEE International Conference on Data Mining Workshops, ICDMW 2023
A2 - Wang, Jihe
A2 - He, Yi
A2 - Dinh, Thang N.
A2 - Grant, Christan
A2 - Qiu, Meikang
A2 - Pedrycz, Witold
PB - IEEE Computer Society
T2 - 23rd IEEE International Conference on Data Mining Workshops, ICDMW 2023
Y2 - 1 December 2023 through 4 December 2023
ER -