Longitudinal Counterfactuals: Constraints and Opportunities (2403.00105v1)
Abstract: Counterfactual explanations are a common approach to providing recourse to data subjects. However, current methodology can produce counterfactuals that cannot be achieved by the subject, making the use of counterfactuals for recourse difficult to justify in practice. Though there is agreement that plausibility is an important quality when using counterfactuals for algorithmic recourse, ground truth plausibility continues to be difficult to quantify. In this paper, we propose using longitudinal data to assess and improve plausibility in counterfactuals. In particular, we develop a metric that compares longitudinal differences to counterfactual differences, allowing us to evaluate how similar a counterfactual is to prior observed changes. Furthermore, we use this metric to generate plausible counterfactuals. Finally, we discuss some of the inherent difficulties of using counterfactuals for recourse.
- The hidden assumptions behind counterfactual explanations and principal reasons. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency. ACM. https://doi.org/10.1145/3351095.3372830
- Multi-Objective Counterfactual Explanations. In Parallel Problem Solving from Nature – PPSN XVI. Springer International Publishing, 448–469. https://doi.org/10.1007/978-3-030-58112-1_31
- Retiring Adult: New Datasets for Fair Machine Learning. Advances in Neural Information Processing Systems 34 (2021).
- CRUDS: Counterfactual Recourse Using Disentangled Subspaces. ICML Workshop on Human Interpretability in Machine Learning (2020), 1–23.
- Integrated Public Use Microdata Series, Current Population Survey: Version 8.0. https://doi.org/10.18128/D030.V8.0
- Riccardo Guidotti. 2022. Counterfactual explanations and how to find them: literature review and benchmarking. Data Mining and Knowledge Discovery (April 2022). https://doi.org/10.1007/s10618-022-00831-6
- MIMIC-III Clinical Database (version 1.4). https://doi.org/10.13026/C2XW26
- MIMIC-III, a freely accessible critical care database. Scientific Data 3, 1 (May 2016). https://doi.org/10.1038/sdata.2016.35
- Algorithmic Recourse: from Counterfactual Explanations to Interventions. CoRR abs/2002.06278 (2020). arXiv:2002.06278 https://arxiv.org/abs/2002.06278
- Achieving Diversity in Counterfactual Explanations: a Review and Discussion. In 2023 ACM Conference on Fairness, Accountability, and Transparency. ACM. https://doi.org/10.1145/3593013.3594122
- Accurate intelligible models with pairwise interactions. In Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Chicago, Illinois, USA) (KDD ’13). Association for Computing Machinery, New York, NY, USA, 623–631. https://doi.org/10.1145/2487575.2487579
- Explaining machine learning classifiers through diverse counterfactual explanations. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency. ACM. https://doi.org/10.1145/3351095.3372850
- FACE. In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society. ACM. https://doi.org/10.1145/3375627.3375850
- ”Why Should I Trust You?”: Explaining the Predictions of Any Classifier. arXiv:1602.04938 [cs.LG]
- GeCo: Quality Counterfactual Explanations in Real Time. arXiv:2101.01292 [cs.LG]
- MIMIC-III and eICU-CRD: Feature Representation by FIDDLE Preprocessing. https://doi.org/10.13026/2QTG-K467
- Democratizing EHR analyses with FIDDLE: a flexible data-driven preprocessing pipeline for structured clinical data. Journal of the American Medical Informatics Association 27, 12 (10 2020), 1921–1934. https://doi.org/10.1093/jamia/ocaa139 arXiv:https://academic.oup.com/jamia/article-pdf/27/12/1921/34838612/ocaa139.pdf
- Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR. CoRR abs/1711.00399 (2017). arXiv:1711.00399 http://arxiv.org/abs/1711.00399