CONFEX: Uncertainty-Aware Counterfactual Explanations with Conformal Guarantees

TL;DR

CONFEX introduces a method for generating reliable counterfactual explanations that incorporate uncertainty guarantees using conformal prediction and MILP, improving robustness and interpretability.

Contribution

It presents a novel uncertainty-aware counterfactual explanation method with formal guarantees, leveraging conformal prediction and tree-based input space partitioning.

Findings

CONFEX provides local coverage guarantees for explanations.

The method achieves robust and plausible explanations across benchmarks.

CONFEX outperforms existing approaches in reliability and interpretability.

Abstract

Counterfactual explanations (CFXs) provide human-understandable justifications for model predictions, enabling actionable recourse and enhancing interpretability. To be reliable, CFXs must avoid regions of high predictive uncertainty, where explanations may be misleading or inapplicable. However, existing methods often neglect uncertainty or lack principled mechanisms for incorporating it with formal guarantees. We propose CONFEX, a novel method for generating uncertainty-aware counterfactual explanations using Conformal Prediction (CP) and Mixed-Integer Linear Programming (MILP). CONFEX explanations are designed to provide local coverage guarantees, addressing the issue that CFX generation violates exchangeability. To do so, we develop a novel localised CP procedure that enjoys an efficient MILP encoding by leveraging an offline tree-based partitioning of the input space. This way, CONFEX generates CFXs with rigorous guarantees on both predictive uncertainty and optimality. We evaluate CONFEX against state-of-the-art methods across diverse benchmarks and metrics, demonstrating that our uncertainty-aware approach yields robust and plausible explanations.