Counterfactual Explanation for Regression via Disentanglement in Latent Space

Xuan Zhao, Klaus Broelemann, Gjergji Kasneci

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 23rd IEEE International Conference on Data Mining Workshops, ICDMW 2023
EditorsJihe Wang, Yi He, Thang N. Dinh, Christan Grant, Meikang Qiu, Witold Pedrycz
PublisherIEEE Computer Society
Pages976-984
Number of pages9
ISBN (Electronic)9798350381641
DOIs
StatePublished - 2023
Event23rd IEEE International Conference on Data Mining Workshops, ICDMW 2023 - Shanghai, China
Duration: 1 Dec 20234 Dec 2023

Publication series

NameIEEE International Conference on Data Mining Workshops, ICDMW
ISSN (Print)2375-9232
ISSN (Electronic)2375-9259

Conference

Conference23rd IEEE International Conference on Data Mining Workshops, ICDMW 2023
Country/TerritoryChina
CityShanghai
Period1/12/234/12/23

Keywords

  • Counterfactual Explaination
  • Regression
  • XAI

Fingerprint

Dive into the research topics of 'Counterfactual Explanation for Regression via Disentanglement in Latent Space'. Together they form a unique fingerprint.

Cite this