Abstract
Counterfactual explanations have become a mainstay of the XAI field. This particularly intuitive statement allows the user to understand what small but necessary changes would have to be made to a given situation in order to change a model prediction. The quality of a counterfactual depends on several criteria: realism, actionability, validity, robustness, etc. In this paper, we are interested in the notion of robustness of a counterfactual. More precisely, we focus on robustness to counterfactual input changes. This form of robustness is particularly challenging as it involves a trade-off between the robustness of the counterfactual and the proximity with the example to explain. We propose a new framework, CROCO, that generates robust counterfactuals while managing effectively this trade-off, and guarantees the user a minimal robustness. An empirical evaluation on tabular datasets confirms the relevance and effectiveness of our approach.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
All proofs are provided in Section A.1 of supplementary material.
- 2.
Function carla.models.catalog.MLModelCatalog of the CARLA library.
- 3.
Watcher is not figured out as it does not set a target for recourse invalidation rate.
References
Artelt, A., et al.: Evaluating robustness of counterfactual explanations. In: Proceedings of the Symposium Series on Computational Intelligence (SSCI), pp. 01–09. IEEE (2021)
Black, E., Wang, Z., Fredrikson, M.: Consistent counterfactuals for deep models. In: Proceedings of the International Conference on Learning Representations (ICLR). OpenReview.net (2022)
Brughmans, D., Leyman, P., Martens, D.: Nice: an algorithm for nearest instance counterfactual explanations. arXiv v2 (2021). arxiv.org/abs/2104.07411
Dominguez-Olmedo, R., Karimi, A.H., Schölkopf, B.: On the adversarial robustness of causal algorithmic recourse. In: Proceedings of the 39th International Conference on Machine Learning (ICML), vol. 162, pp. 5324–5342 (2022)
Ferrario, A., Loi, M.: The robustness of counterfactual explanations over time. Access 10, 82736–82750 (2022)
Guidotti, R.: Counterfactual explanations and how to find them: literature review and benchmarking. Data Min. Knowl. Disc., 1–55 (2022)
Guyomard, V., Fessant, F., Guyet, T.: VCNet: a self-explaining model for realistic counterfactual generation. In: Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), pp. 437–453 (2022)
Laugel, T., Lesot, M.J., Marsala, C., Detyniecki, M.: Issues with post-hoc counterfactual explanations: a discussion. arXiv (2019). arxiv.org/abs/1906.04774
Maragno, D., Kurtz, J., Röber, T.E., Goedhart, R., Birbil, S.I., Hertog, D.D.: Finding regions of counterfactual explanations via robust optimization (2023). arxiv.org/abs/2301.11113
Mishra, S., Dutta, S., Long, J., Magazzeni, D.: A survey on the robustness of feature importance and counterfactual explanations. arXiv (v2) (2023). arxiv.org/abs/2111.00358
Mothilal, R.K., Sharma, A., Tan, C.: Explaining machine learning classifiers through diverse counterfactual explanations. In: Proceedings of the conference on Fairness, Accountability, and Transparency (FAccT), pp. 607–617 (2020)
de Oliveira, R.M.B., Martens, D.: A framework and benchmarking study for counterfactual generating methods on tabular data. Appl. Sci. 11(16), 7274 (2021)
Pawelczyk, M., Bielawski, S., van den Heuvel, J., Richter, T., Kasneci, G.: CARLA: a python library to benchmark algorithmic recourse and counterfactual explanation algorithms. In: Conference on Neural Information Processing Systems (NeurIPS) - Track on Datasets and Benchmarks, p. 17 (2021)
Pawelczyk, M., Broelemann, K., Kasneci, G.: Learning model-agnostic counterfactual explanations for tabular data. In: Proceedings of The Web Conference (WWW 2020), pp. 3126–3132 (2020)
Pawelczyk, M., Datta, T., van-den Heuvel, J., Kasneci, G., Lakkaraju, H.: Probabilistically robust recourse: navigating the trade-offs between costs and robustness in algorithmic recourse. In: Proceedings of the International Conference on Learning Representations (ICLR). OpenReview.net (2023)
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)
Rawal, K., Kamar, E., Lakkaraju, H.: Algorithmic recourse in the wild: understanding the impact of data and model shifts. arXiv v3 (2020). arxiv.org/abs/2012.11788
Upadhyay, S., Joshi, S., Lakkaraju, H.: Towards robust and reliable algorithmic recourse. Adv. Neural Inf. Process. Syst. 34, 16926–16937 (2021)
Ustun, B., Spangher, A., Liu, Y.: Actionable recourse in linear classification. In: Proceedings of the Conference on Fairness, Accountability, and Transparency (FAccT), pp. 10–19 (2019)
Van Looveren, A., Klaise, J.: Interpretable counterfactual explanations guided by prototypes. In: Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML/PKDD), pp. 650–665 (2021)
Virgolin, M., Fracaros, S.: On the robustness of sparse counterfactual explanations to adverse perturbations. Artif. Intell. 316, 103840 (2023)
Wachter, S., Mittelstadt, B.D., Russell, C.: Counterfactual explanations without opening the black box: automated decisions and the GDPR. Harvard J. Law Technol. 31(2), 841–887 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Guyomard, V., Fessant, F., Guyet, T., Bouadi, T., Termier, A. (2023). Generating Robust Counterfactual Explanations. In: Koutra, D., Plant, C., Gomez Rodriguez, M., Baralis, E., Bonchi, F. (eds) Machine Learning and Knowledge Discovery in Databases: Research Track. ECML PKDD 2023. Lecture Notes in Computer Science(), vol 14171. Springer, Cham. https://doi.org/10.1007/978-3-031-43418-1_24
Download citation
DOI: https://doi.org/10.1007/978-3-031-43418-1_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43417-4
Online ISBN: 978-3-031-43418-1
eBook Packages: Computer ScienceComputer Science (R0)
