Optimal Counterfactual Explanations in Tree Ensembles
arXiv:2106.06631
Abstract
Counterfactual explanations are usually generated through heuristics that are sensitive to the search's initial conditions. The absence of guarantees of performance and robustness hinders trustworthiness. In this paper, we take a disciplined approach towards counterfactual explanations for tree ensembles. We advocate for a model-based search aiming at "optimal" explanations and propose efficient mixed-integer programming approaches. We show that isolation forests can be modeled within our framework to focus the search on plausible explanations with a low outlier score. We provide comprehensive coverage of additional constraints that model important objectives, heterogeneous data types, structural constraints on the feature space, along with resource and actionability restrictions. Our experimental analyses demonstrate that the proposed search approach requires a computational effort that is orders of magnitude smaller than previous mathematical programming algorithms. It scales up to large data sets and tree ensembles, where it provides, within seconds, systematic explanations grounded on well-defined models solved to optimality.
arXiv commentAuthors Accepted Manuscript (AAM), to be published in the Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021. Additional typo corrections. Open source code available at https://github.com/vidalt/OCEAN
References in corpus (8)
- Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
- Actionable Recourse in Linear Classification
- The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasons
- Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers
- Algorithmic Recourse: from Counterfactual Explanations to Interventions
- A survey of algorithmic recourse: definitions, formulations, solutions, and prospects
- Born-Again Tree Ensembles
- Ordered Counterfactual Explanation by Mixed-Integer Linear Optimization