Supervised feature compression based on counterfactual analysis
利用反事实解释检测黑箱模型的关键决策边界，构建可调粒度的监督离散化特征，训练出更可解释且紧凑的最优决策树，在真实数据集上验证了准确性和稀疏性。
Counterfactual Explanations are becoming a de-facto standard in post-hoc interpretable machine learning. For a given classifier and an instance classified in an undesired class, its counterfactual explanation corresponds to small perturbations of that instance that allows changing the classification outcome. This work aims to leverage Counterfactual Explanations to detect the important decision boundaries of a pre-trained black-box model. This information is used to build a supervised discretization of the features in the dataset with a tunable granularity. Using the discretized dataset, an optimal Decision Tree can be trained that resembles the black-box model, but that is more interpretable and compact. Numerical results on real-world datasets show the effectiveness of the approach in terms of accuracy and sparsity. • Counterfactual Analysis to discover important boundaries of black-box models. • Definition of a supervised discretization of tunable granularity. • Efficiently train an optimal classification tree using the discretized dataset.