Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)
Preprint
Abstract
Recently, a groundswell of research has identified the use of counterfactual explanations as a potentially significant solution to the Explainable AI (XAI) problem. It is argued that (a) technically, these counterfactual cases can be generated by permuting problem-features until a class change is found, (b) psychologically, they are much more causally informative than factual explanations, (c) legally, they are GDPR-compliant. However, there are issues around the finding of good counterfactuals using current techniques (e.g. sparsity and plausibility). We show that many commonly-used datasets appear to have few good counterfactuals for explanation purposes. So, we propose a new case based approach for generating counterfactuals using novel ideas about the counterfactual potential and explanatory coverage of a case-base. The new technique reuses patterns of good counterfactuals, present in a case-base, to generate analogous counterfactuals that can explain new problems and their solutions. Several experiments show how this technique can improve the counterfactual potential and explanatory coverage of case-bases that were previously found wanting.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- The long road to fairer algorithmsNature, 2020
- Factual and Counterfactual Explanations for Black Box Decision MakingIEEE Intelligent Systems, 2019
- Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)IEEE Access, 2018
- Why a Right to Explanation of Automated Decision-Making Does Not Exist in the General Data Protection RegulationInternational Data Privacy Law, 2017
- Gaining insight through case-based explanationJournal of Intelligent Information Systems, 2008
- A Case-Based Explanation System for Black-Box SystemsArtificial Intelligence Review, 2005
- Explanation in Case-Based Reasoning–Perspectives and GoalsArtificial Intelligence Review, 2005
- Introduction to the Special Issue on Explanation in Case-Based ReasoningArtificial Intelligence Review, 2005
- Family resemblance, conceptual cohesiveness, and category constructionCognitive Psychology, 1987
- The magical number seven, plus or minus two: Some limits on our capacity for processing information.Psychological Review, 1956