Robust Counterfactual Explanations for Random Forests

05/27/2022
by   Alexandre Forel, et al.
0

Counterfactual explanations describe how to modify a feature vector in order to flip the outcome of a trained classifier. Several heuristic and optimal methods have been proposed to generate these explanations. However, the robustness of counterfactual explanations when the classifier is re-trained has yet to be studied. Our goal is to obtain counterfactual explanations for random forests that are robust to algorithmic uncertainty. We study the link between the robustness of ensemble models and the robustness of base learners and frame the generation of robust counterfactual explanations as a chance-constrained optimization problem. We develop a practical method with good empirical performance and provide finite-sample and asymptotic guarantees for simple random forests of stumps. We show that existing methods give surprisingly low robustness: the validity of naive counterfactuals is below 50% on most data sets and can fall to 20% on large problem instances with many features. Even with high plausibility, counterfactual explanations often exhibit low robustness to algorithmic uncertainty. In contrast, our method achieves high robustness with only a small increase in the distance from counterfactual explanations to their initial observations. Furthermore, we highlight the connection between the robustness of counterfactual explanations and the predictive importance of features.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/24/2023

Generating robust counterfactual explanations

Counterfactual explanations have become a mainstay of the XAI field. Thi...
research
01/26/2023

Finding Regions of Counterfactual Explanations via Robust Optimization

Counterfactual explanations play an important role in detecting bias and...
research
10/30/2021

A Survey on the Robustness of Feature Importance and Counterfactual Explanations

There exist several methods that aim to address the crucial task of unde...
research
09/09/2023

Flexible and Robust Counterfactual Explanations with Minimal Satisfiable Perturbations

Counterfactual explanations (CFEs) exemplify how to minimally modify a f...
research
01/29/2022

Counterfactual Plans under Distributional Ambiguity

Counterfactual explanations are attracting significant attention due to ...
research
10/21/2022

Augmentation by Counterfactual Explanation – Fixing an Overconfident Classifier

A highly accurate but overconfident model is ill-suited for deployment i...
research
06/11/2021

Optimal Counterfactual Explanations in Tree Ensembles

Counterfactual explanations are usually generated through heuristics tha...

Please sign up or login with your details

Forgot password? Click here to reset