Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)
2021
Online
Konferenz
Zugriff:
The 28th International Conference on Case-Based Reasoning (ICCBR 2020), Salamanca, Spain, 8–12 June 2020 (held online due to COVID-19 pandemic) ; Recently, a groundswell of research has identified the use of counter-factual explanations as a potentially significant solution to the Explainable AI (XAI) problem. It is argued that (i) technically, these counterfactual cases can be generated by permuting problem-features until a class-change is found, (ii) psychologically, they are much more causally informative than factual explanations, (iii) 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. 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. ; Science Foundation Ireland ; Insight Research Centre
Titel: |
Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)
|
---|---|
Autor/in / Beteiligte Person: | Smyth, Barry ; Keane, Mark T. |
Link: | |
Veröffentlichung: | 2021 |
Medientyp: | Konferenz |
DOI: | 10.1007/978-3-030-58342-2_11 |
Schlagwort: |
|
Sonstiges: |
|