Finding Regions of Counterfactual Explanations via Robust Optimization
Authors:
- Donato MaragnoDMDonato Maragno
- Jannis KurtzJKJannis Kurtz
- Tabea E. RöberTRTabea E. Röber
- Rob GoedhartRGRob Goedhart
- Ş. Ilker BirbilŞBŞ. Ilker Birbil
- Dick Den HertogDHDick Den Hertog
Preprint
Abstract
Counterfactual explanations play an important role in detecting bias and improving the explainability of data-driven classification models. A counterfactual explanation (CE) is a minimal perturbed data point for which the decision of the model changes. Most of the existing methods can only provide one CE, which may not be achievable for the user. In this work we derive an iterative method to calculate robust CEs, i.e. CEs that remain valid even after the features are slightly perturbed. To this end, our method provides a whole region of CEs allowing the user to choose a suitable recourse to obtain a desired outcome. We use algorithmic ideas from robust optimization and prove convergence results for the most common machine learning methods including logistic regression, decision trees, random forests, and neural networks. Our experiments show that our method can efficiently generate globally optimal robust CEs for a variety of common data sets and classification models.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- Mixed-Integer Optimization with Constraint LearningOperations Research, 2025
- On the robustness of sparse counterfactual explanations to adverse perturbationsArtificial Intelligence, 2022
- The Robustness of Counterfactual Explanations Over TimeIEEE Access, 2022
- Evaluating Robustness of Counterfactual Explanations2021
- Strong mixed-integer programming formulations for trained neural networksMathematical Programming, 2020
- ReLU networks as surrogate models in mixed-integer linear programsComputers & Chemical Engineering, 2019
- Robust Optimization2009
- Cutting-set methods for robust convex optimization with pessimizing oraclesOptimization Methods and Software, 2009