Counterfactual explanations and how to find them: literature review and benchmarking

• Published in: Data mining and knowledge discovery Vol. 38; no. 5; pp. 2770 - 2824
• Main Author: Guidotti, Riccardo
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.09.2024; Springer Nature B.V
• Subjects: Artificial Intelligence; Benchmarks; Chemistry and Earth Sciences; Cognition & reasoning; Computer Science; Customers; Data Mining and Knowledge Discovery; Information Storage and Retrieval; Leasing; Literature reviews; Machine learning; Physics; Special Issue on Explainable and Interpretable Machine Learning and Data Mining; Statistics for Engineering; Interpretable machine learning; Counterfactual explanations; Contrastive explanations; Explainable AI
• ISSN: 1384-5810; 1573-756X
• DOI: 10.1007/s10618-022-00831-6

Interpretable machine learning aims at unveiling the reasons behind predictions returned by uninterpretable classifiers. One of the most valuable types of explanation consists of counterfactuals. A counterfactual explanation reveals what should have been different in an instance to observe a diverse outcome. For instance, a bank customer asks for a loan that is rejected. The counterfactual explanation consists of what should have been different for the customer in order to have the loan accepted. Recently, there has been an explosion of proposals for counterfactual explainers. The aim of this work is to survey the most recent explainers returning counterfactual explanations. We categorize explainers based on the approach adopted to return the counterfactuals, and we label them according to characteristics of the method and properties of the counterfactuals returned. In addition, we visually compare the explanations, and we report quantitative benchmarking assessing minimality, actionability, stability, diversity, discriminative power, and running time. The results make evident that the current state of the art does not provide a counterfactual explainer able to guarantee all these properties simultaneously.