An ASP-Based Approach to Counterfactual Explanations for Classification
Machine Learning
2020-06-17 v2 Databases
Logic in Computer Science
Machine Learning
Abstract
We propose answer-set programs that specify and compute counterfactual interventions as a basis for causality-based explanations to decisions produced by classification models. They can be applied with black-box models and models that can be specified as logic programs, such as rule-based classifiers. The main focus in on the specification and computation of maximum responsibility causal explanations. The use of additional semantic knowledge is investigated.
Cite
@article{arxiv.2004.13237,
title = {An ASP-Based Approach to Counterfactual Explanations for Classification},
author = {Leopoldo Bertossi},
journal= {arXiv preprint arXiv:2004.13237},
year = {2020}
}
Comments
Revised and extended version. To appear in Proc. RuleML+RR, 2020