CONFEX: Uncertainty-Aware Counterfactual Explanations with Conformal Guarantees
This work addresses the need for trustworthy and actionable explanations in machine learning, particularly for users requiring interpretability, though it is incremental by building on existing methods with formal guarantees.
The paper tackled the problem of generating reliable counterfactual explanations by addressing predictive uncertainty, proposing CONFEX, which uses Conformal Prediction and Mixed-Integer Linear Programming to provide local coverage guarantees and robust explanations.
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.