Article

Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)

Authors:

Barry SmythAuthors Info & Claims

Case-Based Reasoning Research and Development: 28th International Conference, ICCBR 2020, Salamanca, Spain, June 8–12, 2020, Proceedings

Pages 163 - 178

https://doi.org/10.1007/978-3-030-58342-2_11

Published: 08 June 2020 Publication History

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 (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. 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.

References

[1]

Gunning, D.: Explainable artificial intelligence (XAI). Defense Advanced Research Projects Agency (DARPA), Web, vol. 2 (2017)

[2]

Gunning D and Aha DW DARPA’s explainable artificial intelligence program AI Mag. 2019 40 2 44-58

[3]

Goodman B and Flaxman S European Union regulations on algorithmic decision-making and a “right to explanation” AI Mag. 2017 38 3 50-57

[4]

Wachter S, Mittelstadt B, and Floridi L Why a right to explanation of automated decision-making does not exist in the general data protection regulation Int. Data Priv. Law 2017 7 2 76-99

[5]

Adadi A and Berrada M Peeking inside the black-box: a survey on Explainable Artificial Intelligence (XAI) IEEE Access 2018 6 52138-52160

[6]

Guidotti R, Monreale A, Ruggieri S, Turini F, Giannotti F, and Pedreschi D A survey of methods for explaining black box models ACM Comput. Surv. 2018 51 5 93

[7]

Miller TExplanation in artificial intelligenceArtif. Intell.20192671-3807099170

[8]

Leake, D.B.: CBR in context: the present and future. In: Case-Based Reasoning: Experiences, Lessons, and Future Directions, pp. 3–30 (1996)

[9]

Leake D and McSherry D Introduction to the special issue on explanation in case-based reasoning Artif. Intell. Rev. 2005 24 2 103-108

[10]

Sørmo F, Cassens J, and Aamodt AExplanation in case-based reasoning–perspectives and goalsArtif. Intell. Rev.2005242109-1431086.68604

[11]

Schoenborn, J.M., Althoff, K.D.: Recent trends in XAI: In: Case-Based Reasoning for the Explanation of intelligent systems (XCBR) Workshop (2019)

[12]

Lipton ZC The Mythos of model interpretability Queue 2018 16 3 30

[13]

Kenny, E.M., Keane, M.T.: Twin-systems to explain neural networks using case-based reasoning. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019, pp. 326–333 (2019)

[14]

Keane MT and Kenny EM Bach K and Marling C How case-based reasoning explains neural networks: a theoretical analysis of XAI using Post-Hoc explanation-by-example from a survey of ANN-CBR twin-systems Case-Based Reasoning Research and Development 2019 Cham Springer 155-171

[15]

Byrne, R.M.J.: The Rational Imagination. MIT Press, Cambridge (2007)

[16]

Byrne, R.M.J.: Counterfactuals in explainable artificial intelligence (XAI): evidence from human reasoning. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI 2019, pp. 6276–6282 (2019)

[17]

Wachter S, Mittelstadt B, and Russell C Counterfactual explanations without opening the black box: automated decisions and the GDPR Harv. J. Law Tech. 2018 31 841

[18]

Guidotti, R., Monreale, A., Giannotti, F., Pedreschi, D., Ruggieri S., Turini. F.: Factual and counterfactual explanations for black box decision making. IEEE Intell. Syst. 34(6), 14–23 (2019)

[19]

Smyth, B., Keane, M.T.: Remembering to forget. In: Proceedings of the 14th International Joint Conference on Artificial Intelligence, IJCAI 1995, pp. 377–382 (1995)

[20]

Smyth B and McKenna E Smyth B and Cunningham P Modelling the competence of case-bases Advances in Case-Based Reasoning 1998 Heidelberg Springer 208-220

[21]

Juarez, J.M., Craw, S., Lopez-Delgado, J.R., Campos, M.: Maintenance of case-bases: current algorithms after fifty years. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018, pp. 5457–5463 (2018)

[22]

Delany SJ, Cunningham P, Doyle D, and Zamolotskikh A Muñoz-Ávila H and Ricci F Generating estimates of classification confidence for a case-based spam filter Case-Based Reasoning Research and Development 2005 Heidelberg Springer 177-190

[23]

Kumar RR, Viswanath P, and Bindu CS Nearest neighbor classifiers: a review Int. J. Comput. Intell. Res. 2017 13 2 303-311

[24]

Cunningham P, Doyle D, and Loughrey J Ashley KD and Bridge DG An evaluation of the usefulness of case-based explanation Case-Based Reasoning Research and Development 2003 Heidelberg Springer 122-130

[25]

Nugent C and Cunningham PA case-based explanation system for black-box systemsArtif. Intell. Rev.2005242163-1781083.68612

[26]

Mittelstadt, B., Russell, C., Wachter, S.: Explaining explanations in AI. In: Proceedings of Conference on Fairness, Accountability, and Transparency, FAT 2019 (2019)

[27]

Pearl, J.: Causality, Cambridge University Press, Cambridge (2000)

[28]

Sokol, K., Flach, P.: Desiderata for interpretability: explaining decision tree predictions with counterfactuals. In: AAAI 20119, Doctoral Consortium, pp. 10035–10036 (2019)

[29]

Poyiadzi, R., Sokol, K., Santos-Rodriguez, R., De Bie, T., Flach, P.: FACE: feasible and actionable counterfactual explanations. In: Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, pp. 344–350 (2020). 10.1145/3375627.3375850

[30]

Woodward, J.: Making Things Happen. Oxford University Press, Oxford (2003)

[31]

Van Fraassen, B.C.: The Scientific Image. Oxford University Press, Oxford (1980)

[32]

Kahneman D and Miller DT Norm theory: comparing reality to its alternatives Psychol. Rev. 1986 93 2 136-153

[33]

Mueller, S.T., Hoffman, R.R., Clancey, W.J., Emery, A.K., Klein, G.: Explanation in human-AI systems. Florida Institute for Human and Machine Cognition (2019)

[34]

Dodge, J., Liao, Q.V., Zhang, Y., Bellamy, R.K., Dugan, C.: Explaining models: an empirical study of how explanations impact fairness judgment. In: Proceedings of the 24th International Conference on Intelligent User Interfaces, pp. 275–285 (2019)

[35]

Miller, T.: Contrastive explanation. arXiv preprint arXiv:1811.03163 (2018)

[36]

Russell, C., Kusner, M.J., Loftus, J., Silva, R.: When worlds collide: integrating different counterfactual assumptions in fairness. In: Advances in Neural Information Processing Systems, pp. 6414–6423 (2017)

[37]

Ribeiro, M.T., Singh, S., Guestrin, C.: Why should I trust you?. In: Proceedings of the 22nd ACM SIGKDD, pp. 1135–1144. ACM (2016)

[38]

Pedreschi, D., Giannotti, F., Guidotti, R., Monreale, A., Ruggieri, S., Turini, F.: Meaningful explanations of Black Box AI decision systems. In: Proceedings of AAAI 2019 (2019)

[39]

Mothilal, R.K., Sharma, A., Tan, C.: Explaining machine learning classifiers through diverse counterfactual explanations. In: Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, FAT 2020, pp. 607–617 (2020)

[40]

McGrath, R., et al.: Interpretable credit application predictions with counterfactual explanations. In: NIP Workshop on Challenges and Opportunities for AI in Financial Services, Montreal, Canada (2018)

[41]

Miller GA The magical number seven, plus or minus two: some limits on our capacity for processing information Psychol. Rev. 1956 63 2 81

[42]

Alvarez G and Cavanagh P The capacity of visual STM is set both by visual information load and by number of objects Psychol. Sci. 2004 15 106-111

[43]

Medin DL, Wattenmaker WD, and Hampson SE Family resemblance, conceptual cohesiveness, and category construction Cogn. Psychol. 1987 19 2 242-279

[44]

Laugel, T., Lesot, M.J., Marsala, C., Renard, X., Detyniecki, M.: The dangers of post-hoc interpretability: unjustified counterfactual explanations. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019, pp. 2801–2807 (2019)

[45]

Dua, D., Graff, C.: UCI Machine Learning Repository University of California, School of Information and Computer Science, Irvine, CA. http://archive.ics.uci.edu/ml (2019)

[46]

Lieber J, Nauer E, and Prade H Bach K and Marling C Improving analogical extrapolation using case pair competence Case-Based Reasoning Research and Development 2019 Cham Springer 251-265

[47]

Veale, T., Keane, M.T.: The competence of sub-optimal theories of structure mapping on hard analogies. In: International Joint Conference on Artificial Intelligence, pp. 232–237 (1997)

[48]

Keane MT Wess S, Althoff KD, and Richter MM Analogical asides on case-based reasoning Topics in Case-Based Reasoning 1994 Heidelberg Springer 21-32

[49]

Karimi, A.H., Barthe, G., Balle, B., Valera, I.: Model-agnostic counterfactual explanations for consequential decisions. In: Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, AISTATS 2020, Palermo, Italy, vol. 108. PMLR (2020)

[50]

Sokol, K., Flach, P.: Explainability fact sheets: a framework for systematic assessment of explainable approaches. In: Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, FAT 2020, pp. 56–67 (2020)

Cited By

Nannini LHuyskes DPanai EPistilli GTartaro A(2025)Nullius in Explanans: an ethical risk assessment for explainable AIEthics and Information Technology10.1007/s10676-024-09800-727:1Online publication date: 1-Mar-2025
https://dl.acm.org/doi/10.1007/s10676-024-09800-7
Koh SKim BJo S(2024)Understanding the User Perception and Experience of Interactive Algorithmic Recourse CustomizationACM Transactions on Computer-Human Interaction10.1145/367450331:3(1-25)Online publication date: 30-Aug-2024
https://dl.acm.org/doi/10.1145/3674503
Warren GByrne RKeane M(2024)Categorical and Continuous Features in Counterfactual Explanations of AI SystemsACM Transactions on Interactive Intelligent Systems10.1145/367390714:4(1-37)Online publication date: 20-Jun-2024
https://dl.acm.org/doi/10.1145/3673907
Show More Cited By

Index Terms

Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)
1. Computing methodologies
  1. Artificial intelligence
  2. Machine learning
2. Theory of computation

Index terms have been assigned to the content through auto-classification.

Recommendations

The Use and Misuse of Counterfactuals in Ethical Machine Learning
FAccT '21: Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency

The use of counterfactuals for considerations of algorithmic fairness and explainability is gaining prominence within the machine learning community and industry. This paper argues for more caution with the use of counterfactuals when the facts to be ...
“Better” Counterfactuals, Ones People Can Understand: Psychologically-Plausible Case-Based Counterfactuals Using Categorical Features for Explainable AI (XAI)
Case-Based Reasoning Research and Development
Abstract
A recent surge of research has focused on counterfactual explanations as a promising solution to the eXplainable AI (XAI) problem. Over 100 counterfactual XAI methods have been proposed, many emphasising the key role of features that are “...
Explainable AI and Causal Understanding: Counterfactual Approaches Considered
Abstract
The counterfactual approach to explainable AI (XAI) seeks to provide understanding of AI systems through the provision of counterfactual explanations. In a recent systematic review, Chou et al. (Inform Fus 81:59–83, 2022) argue that the ...

Comments

Information & Contributors

Information

Published In

cover image Guide Proceedings

Case-Based Reasoning Research and Development: 28th International Conference, ICCBR 2020, Salamanca, Spain, June 8–12, 2020, Proceedings

Jun 2020

359 pages

ISBN:978-3-030-58341-5

DOI:10.1007/978-3-030-58342-2

Editors:
Ian Watson
School of Computer Science, University of Auckland, Auckland, New Zealand
,
Rosina Weber
College of Computing and Informatics, Drexel University, Philadelphia, PA, USA

© Springer Nature Switzerland AG 2020.

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 08 June 2020

Author Tags

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

30
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 12 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Nannini LHuyskes DPanai EPistilli GTartaro A(2025)Nullius in Explanans: an ethical risk assessment for explainable AIEthics and Information Technology10.1007/s10676-024-09800-727:1Online publication date: 1-Mar-2025
https://dl.acm.org/doi/10.1007/s10676-024-09800-7
Koh SKim BJo S(2024)Understanding the User Perception and Experience of Interactive Algorithmic Recourse CustomizationACM Transactions on Computer-Human Interaction10.1145/367450331:3(1-25)Online publication date: 30-Aug-2024
https://dl.acm.org/doi/10.1145/3674503
Warren GByrne RKeane M(2024)Categorical and Continuous Features in Counterfactual Explanations of AI SystemsACM Transactions on Interactive Intelligent Systems10.1145/367390714:4(1-37)Online publication date: 20-Jun-2024
https://dl.acm.org/doi/10.1145/3673907
Retzlaff CAngerschmid ASaranti ASchneeberger DRöttger RMüller HHolzinger A(2024)Post-hoc vs ante-hoc explanationsCognitive Systems Research10.1016/j.cogsys.2024.10124386:COnline publication date: 18-Jul-2024
https://dl.acm.org/doi/10.1016/j.cogsys.2024.101243
Parsodkar AP. DChakraborti S(2024)Navigating the Landscape of Case Fidelity and Competence in Case-Based ReasoningArtificial Intelligence XLI10.1007/978-3-031-77915-2_17(235-249)Online publication date: 17-Dec-2024
https://dl.acm.org/doi/10.1007/978-3-031-77915-2_17
Aryal SKeane M(2024)Even-Ifs from If-Onlys: Are the Best Semi-factual Explanations Found Using Counterfactuals as Guides?Case-Based Reasoning Research and Development10.1007/978-3-031-63646-2_3(33-49)Online publication date: 1-Jul-2024
https://dl.acm.org/doi/10.1007/978-3-031-63646-2_3
Sen AMainali MRauch CAddison UFloyd MGoel PKarneeb JKulhanek RLarue OMénager DMolineaux MTurner JWeber R(2024)Counterfactual-Based Synthetic Case GenerationCase-Based Reasoning Research and Development10.1007/978-3-031-63646-2_25(388-403)Online publication date: 1-Jul-2024
https://dl.acm.org/doi/10.1007/978-3-031-63646-2_25
Warren GDelaney EGuéret CKeane M(2024)Explaining Multiple Instances Counterfactually:User Tests of Group-Counterfactuals for XAICase-Based Reasoning Research and Development10.1007/978-3-031-63646-2_14(206-222)Online publication date: 1-Jul-2024
https://dl.acm.org/doi/10.1007/978-3-031-63646-2_14
Goethals SSörensen KMartens D(2023)The Privacy Issue of Counterfactual Explanations: Explanation Linkage AttacksACM Transactions on Intelligent Systems and Technology10.1145/360848214:5(1-24)Online publication date: 11-Aug-2023
https://dl.acm.org/doi/10.1145/3608482
Warren GByrne RKeane M(2023)Categorical and Continuous Features in Counterfactual Explanations of AI SystemsProceedings of the 28th International Conference on Intelligent User Interfaces10.1145/3581641.3584090(171-187)Online publication date: 27-Mar-2023
https://dl.acm.org/doi/10.1145/3581641.3584090
Show More Cited By

View Options

View options

Figures

Tables

Media

View Table of Conten