ORIGINAL RESEARCH article
Front. Artif. Intell.
Sec. AI in Finance
This article is part of the Research TopicAI's Revolution in Credit Risk: From Traditional Models to Neural NetworksView all articles
Tabular Diffusion Counterfactual Explanations
Provisionally accepted
- 1Columbia University, New York City, United States
- 2Capital One Financial Corp, McLean, United States
- 3Columbia University, New York, United States
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
ABSTRACT Counterfactual explanations methods provide an important tool in the field of interpretable machine learning. Recent advances in this direction have focused on diffusion models to explain a deep classifier. However, these techniques have predominantly focused on problems in computer vision. In this paper, we focus on tabular data typical in finance and the social sciences and propose a novel guided reverse process for categorical features based on an approximation to the Gumbel-softmax distribution. Furthermore, we study the effect of the temperature τ and derive a theoretical bound between the Gumbel-softmax distribution and our proposed approximated distribution. We perform experiments on several large-scale credit lending and other tabular datasets, assessing their performance in terms of the quantitative measures of interpretability, diversity, instability, and validity. These results indicate that our approach outperforms popular baseline methods, producing robust and realistic counterfactual explanations.
Keywords: Controllable Diffusion Models, Counterfactual generation, Deterogeneous Data, Discrete Diffusion Models, Explainable Machine Learning
Received: 10 Nov 2025; Accepted: 21 Jan 2026.
Copyright: © 2026 Zhang, Barr and Paisley. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Wei Zhang
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.