Prototype-based Counterfactual Explanation for Causal Classification

05/03/2021 ∙ by Tri Dung Duong, et al. ∙ 0

Counterfactual explanation is one branch of interpretable machine learning that produces a perturbation sample to change the model's original decision. The generated samples can act as a recommendation for end-users to achieve their desired outputs. Most of the current counterfactual explanation approaches are the gradient-based method, which can only optimize the differentiable loss functions with continuous variables. Accordingly, the gradient-free methods are proposed to handle the categorical variables, which however present several major limitations: 1) causal relationships among features are typically ignored when generating the counterfactuals, possibly resulting in impractical guidelines for decision-makers; 2) the generation of the counterfactual sample is prohibitively slow and requires lots of parameter tuning for combining different loss functions. In this work, we propose a causal structure model to preserve the causal relationship underlying the features of the counterfactual. In addition, we design a novel gradient-free optimization based on the multi-objective genetic algorithm that generates the counterfactual explanations for the mixed-type of continuous and categorical data. Numerical experiments demonstrate that our method compares favorably with state-of-the-art methods and therefore is applicable to any prediction model. All the source code and data are available at <>.



There are no comments yet.


page 1

page 2

page 3

page 4

Code Repositories



view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.