Counterfactual explanations and how to find them: literature review and benchmarking-Reference-Cited by-同舟云学术

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

Published:2022-04-28 Issue: Volume: Page:
ISSN:1384-5810
Container-title:Data Mining and Knowledge Discovery
language:en
Short-container-title:Data Min Knowl Disc

Author:

Guidotti Riccardo^ORCID

Abstract

AbstractInterpretable 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.

Funder

SoBigData++

HumanE AI Net

XAI

TAILOR

Publisher

Springer Science and Business Media LLC

Subject

Computer Networks and Communications,Computer Science Applications,Information Systems

Link

https://link.springer.com/content/pdf/10.1007/s10618-022-00831-6.pdf

Reference152 articles.

1. Aamodt A, Plaza E (1994) Case-based reasoning: foundational issues, methodological variations, and system approaches. AI Commun 7(1):39–59

2. Adadi A et al (2018) Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6:52138–52160

3. Aggarwal CC, Chen C, Han J (2010) The inverse classification problem. J Comput Sci Technol 25(3):458–468

4. Anjomshoae S, Najjar A, Calvaresi D, Främling K (2019) Explainable agents and robots: results from a systematic literature review. In: Proceedings of the 18th international conference on autonomous agents and multiagent systems, AAMAS’19, Montreal, QC, Canada, May 13–17, 2019, International Foundation for Autonomous Agents and Multiagent Systems, pp 1078–1088

5. Arrieta AB, Ser JD (2020) Plausible counterfactuals: auditing deep learning classifiers with realistic adversarial examples. In: 2020 International joint conference on neural networks, IJCNN 2020, Glasgow, United Kingdom, July 19–24, 2020, IEEE, pp 1–7

Cited by 125 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Mathematical optimization modelling for group counterfactual explanations;European Journal of Operational Research;2024-12

2. Explainable time series anomaly detection using masked latent generative modeling;Pattern Recognition;2024-12

3. Beyond model interpretability: socio-structural explanations in machine learning;AI & SOCIETY;2024-09-05

4. Explainable artificial intelligence: A survey of needs, techniques, applications, and future direction;Neurocomputing;2024-09

5. Tertiary Review on Explainable Artificial Intelligence: Where Do We Stand?;Machine Learning and Knowledge Extraction;2024-08-30