Flexible and Robust Counterfactual Explanations with Minimal Satisfiable Perturbations

Abstract

Counterfactual explanations (CFEs) exemplify how to minimally modify a feature vector to achieve a different prediction for an instance. CFEs can enhance informational fairness and trustworthiness, and provide suggestions for users who receive adverse predictions. However, recent research has shown that multiple CFEs can be offered for the same instance or instances with slight differences. Multiple CFEs provide flexible choices and cover diverse desiderata for user selection. However, individual fairness and model reliability will be damaged if unstable CFEs with different costs are returned. Existing methods fail to exploit flexibility and address the concerns of non-robustness simultaneously. To address these issues, we propose a conceptually simple yet effective solution named Counterfactual Explanations with Minimal Satisfiable Perturbations (CEMSP). Specifically, CEMSP constrains changing values of abnormal features with the help of their semantically meaningful normal ranges. For efficiency, we model the problem as a Boolean satisfiability problem to modify as few features as possible. Additionally, CEMSP is a general framework and can easily accommodate more practical requirements, e.g., casualty and actionability. Compared to existing methods, we conduct comprehensive experiments on both synthetic and real-world datasets to demonstrate that our method provides more robust explanations while preserving flexibility.

arXiv commentAccepted by CIKM 2023

References in corpus (15)

• Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
• Actionable Recourse in Linear Classification
• CERTIFAI: Counterfactual Explanations for Robustness, Transparency, Interpretability, and Fairness of Artificial Intelligence models
• Learning Model-Agnostic Counterfactual Explanations for Tabular Data
• Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweaking
• Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems
• Algorithmic recourse under imperfect causal knowledge: a probabilistic approach
• "There Is Not Enough Information": On the Effects of Explanations on Perceptions of Informational Fairness and Trustworthiness in Automated Decision-Making
• Generalized Inverse Classification
• Inverse Classification for Comparison-based Interpretability in Machine Learning
• Towards Robust and Reliable Algorithmic Recourse
• Issues with post-hoc counterfactual explanations: a discussion
• On Counterfactual Explanations under Predictive Multiplicity
• Robust Counterfactual Explanations for Tree-Based Ensembles
• Consistent Counterfactuals for Deep Models