Counterfactual Explanations for Cautious Random Forests
ACM Transactions on Knowledge Discovery from Data · 30.04.2026 · 20 (3) · 1-35
DOI: 10.1145/3794856 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Knowledge Discovery from Data, online erschienen am 23.03.2026. Verfasst von Haifei Zhang und 2 weiteren Autor:innen. Die Arbeit nennt 61 Literaturangaben. Gefördert von: Université de Technologie de Compiègne and its subsidiary UTeam.
Abstract (Originalsprache)
Traditional machine learning models provide a single-class prediction for a given input instance. This may be inadequate in some scenarios, especially when the cost of erroneous predictions is high. Cautious random forests are cautious classification models that may output sets of possible classes as predictions when uncertainty is high, thus reducing the risk of making incorrect decisions. However, making such indeterminate predictions carries a cost, as resolving indeterminacy typically necessitates further analysis and manual intervention. This work focuses on explaining why an indeterminate prediction has been made and how indeterminacy can be resolved. To this end, we use counterfactual examples associated with determinate predictions. We propose a branch-and-bound algorithm that can efficiently generate proximal, plausible, and actionable counterfactual examples. Several experimental results are presented to demonstrate the advantages of our proposed method.
Förderung
- Université de Technologie de Compiègne and its subsidiary UTeam
Zitieren
APA
Zhang, H., Quost, B., & Masson, M. (2026). Counterfactual Explanations for Cautious Random Forests. ACM Transactions on Knowledge Discovery from Data, 20(3), 1-35. https://doi.org/10.1145/3794856
Vancouver
Zhang H, Quost B, Masson M. Counterfactual Explanations for Cautious Random Forests. ACM Transactions on Knowledge Discovery from Data. 2026;20(3):1-35. doi:10.1145/3794856
BibTeX
@article{Zhang2026,
author = {Zhang, Haifei and Quost, Benjamin and Masson, Marie-Hélène},
title = {Counterfactual Explanations for Cautious Random Forests},
journal = {ACM Transactions on Knowledge Discovery from Data},
year = {2026},
volume = {20},
number = {3},
pages = {1--35},
doi = {10.1145/3794856}
}
EUVIMED