Local and Regional Counterfactual Rules: Summarized and Robust Recourses
Salim I. Amoukou, Nicolas J.B Brunel

TL;DR
This paper introduces a probabilistic framework for generating stable, sparse, and robust counterfactual explanations using Random Forests, which summarize diverse explanations into local and regional rules with statistical guarantees.
Contribution
It proposes a novel probabilistic approach for local and regional counterfactual rules that improve stability, sparsity, and robustness, derived from Random Forests with statistical guarantees.
Findings
Rules are sparse and high-density based.
Regional rules identify shared recourses for subgroups.
Experiments show improved robustness over standard methods.
Abstract
Counterfactual Explanations (CE) face several unresolved challenges, such as ensuring stability, synthesizing multiple CEs, and providing plausibility and sparsity guarantees. From a more practical point of view, recent studies [Pawelczyk et al., 2022] show that the prescribed counterfactual recourses are often not implemented exactly by individuals and demonstrate that most state-of-the-art CE algorithms are very likely to fail in this noisy environment. To address these issues, we propose a probabilistic framework that gives a sparse local counterfactual rule for each observation, providing rules that give a range of values capable of changing decisions with high probability. These rules serve as a summary of diverse counterfactual explanations and yield robust recourses. We further aggregate these local rules into a regional counterfactual rule, identifying shared recourses for…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsExplainable Artificial Intelligence (XAI) · Bayesian Modeling and Causal Inference · Data Stream Mining Techniques
