Tabular Diffusion Counterfactual Explanations
This work addresses the need for interpretable machine learning in domains like finance and social sciences, where tabular data is common, by extending diffusion-based counterfactual explanation methods from computer vision to tabular settings, representing an incremental advancement.
The paper tackles the problem of generating counterfactual explanations for tabular data, typical in finance and social sciences, by proposing a novel guided reverse process for categorical features based on an approximation to the Gumbel-softmax distribution, and it shows that this approach outperforms popular baseline methods in terms of interpretability, diversity, instability, and validity.
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.