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

被引：197
作者：
Guidotti, Riccardo [1 ]
机构：
[1] Univ Pisa, Largo B Pontecorvo 3, I-56127 Pisa, PI, Italy
来源：
DATA MINING AND KNOWLEDGE DISCOVERY | 2024年 / 38卷 / 05期
基金：
欧盟地平线“2020”;
关键词：
Explainable AI; Counterfactual explanations; Contrastive explanations; Interpretable machine learning; INVERSE CLASSIFICATION; BLACK-BOX; MACHINE; INTERPRETABILITY; GENERATION; SELECTION; SUPPORT;
D O I：
10.1007/s10618-022-00831-6
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
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.
引用
收藏
页码：2770 / 2824
页数：55
相关论文
共 149 条
[1]  
AAMODT A, 1994, AI COMMUN, V7, P39
[2]   Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) [J].
Adadi, Amina ;
Berrada, Mohammed .
IEEE ACCESS, 2018, 6 :52138-52160
[3]   The Inverse Classification Problem [J].
Aggarwal, Charu C. ;
Chen, Chen ;
Han, Jiawei .
JOURNAL OF COMPUTER SCIENCE AND TECHNOLOGY, 2010, 25 (03) :458-468
[4]  
Anjomshoae S, 2019, AAMAS '19: PROCEEDINGS OF THE 18TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS, P1078
[5]   A Tool for the Automatic Generation of Test Cases and Oracles for Simulation Models Based on Functional Requirements [J].
Arrieta, Aitor ;
Agirre, Joseba A. ;
Sagardui, Goiuria .
2020 IEEE 13TH INTERNATIONAL CONFERENCE ON SOFTWARE TESTING, VERIFICATION AND VALIDATION WORKSHOPS (ICSTW), 2020, :1-5
[6]  
Artelt A, 2021, ARXIV210302354
[7]  
Artelt A., 2019, ARXIV191107749
[8]  
Artelt A, 2020, 28 EUR S ART NEUR NE, P19
[9]   Convex Density Constraints for Computing Plausible Counterfactual Explanations [J].
Artelt, Andre ;
Hammer, Barbara .
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2020, PT I, 2020, 12396 :353-365
[10]  
Artelt Andre, 2019, CEML: Counterfactuals for Explaining Machine Learning models-A Python toolbox
12345678910