Improving Counterfactual Truthfulness for Molecular Property Prediction through Uncertainty Quantification

Understand

Explainable AI (xAI) interventions aim to improve interpretability for complex black-box models, not only to improve user trust but also as a means to extract scientific insights from high-performing predictive systems.

• In molecular property prediction, counterfactual explanations offer a way to understand predictive behavior by highlighting which minimal perturbations in the input molecular structure cause the greatest deviation in the predicted property.
• However, such explanations only allow for meaningful scientific insights if they reflect the distribution of the true underlying property -- a feature we define as counterfactual truthfulness.
• To increase this truthfulness, we propose the integration of uncertainty estimation techniques to filter counterfactual candidates with high predicted uncertainty.