Explainable GNNs in Chemistry: Combining Attribution and Uncertainty Quantification

29 April 2025, Version 1
This content is a preprint and has not undergone peer review at the time of posting.

Abstract

Graph Neural Networks (GNNs) are powerful tools for predicting chemical properties, but their black-box nature can limit trust and utility. Explainability through feature attribution and awareness of prediction uncertainty are critical for practical applications, for example in iterative lab-in-the-loop scenarios. We systematically evaluate different post-hoc feature attribution methods and study their integration with epistemic uncertainty quantification in GNNs for chemistry. Our findings reveal a strong synergy: attributing uncertainty to specific input features (atoms or substructures) provides a granular understanding of model confidence and highlights potential data gaps or model limitations. We evaluated several attribution approaches on aqueous solubility and molecular weight prediction tasks, demonstrating that methods like Feature Ablation and Shapley Value Sampling can effectively identify molecular substructures driving prediction and its uncertainty. This combined approach significantly enhances the interpretability and actionable insights derived from chemical GNNs, facilitating the design or more useful models in research and development.

Keywords

Explainable AI
Feature Attribution
Uncertainty Quantification
Graph Neural Networks
Solubility
Shapley

Comments

Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.