CONFEX: Uncertainty-Aware Counterfactual Explanations with Conformal Guarantees

2025-10-22

AI Summary

Existing counterfactual explanation methods largely ignore predictive uncertainty, resulting in unreliable explanations. To address this, we propose an uncertainty-aware counterfactual generation framework. First, we design a localized conformal prediction mechanism that overcomes the exchangeability violation inherent in counterfactual generation—enabling, for the first time, statistically rigorous coverage guarantees for uncertainty-aware counterfactuals. Second, we integrate conformal prediction with mixed-integer linear programming and tree-based offline partitioning of the input space, achieving both theoretical reliability and improved computational efficiency. Extensive experiments on multiple benchmark datasets demonstrate that our method generates counterfactuals exhibiting superior robustness, plausibility, and credibility—outperforming state-of-the-art approaches by significant margins.

Technology Category

• Reasoning under Uncertainty: Causality
• Machine Learning: Calibration & Uncertainty Quantification
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

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.

Problem

• Generating counterfactual explanations with uncertainty awareness
• Providing local coverage guarantees for explanation reliability
• Addressing exchangeability violation in counterfactual generation process

Innovation

• Uses conformal prediction for uncertainty-aware explanations
• Employs mixed-integer linear programming for optimization
• Leverages tree-based partitioning for efficient local guarantees