Fragment-Wise Interpretability in Graph Neural Networks via Molecule Decomposition and Contribution Analysis
This addresses the problem of trust in AI predictions for domain experts in drug discovery and materials design, offering an incremental improvement in interpretability techniques.
The paper tackled the lack of interpretability in graph neural networks for molecular property prediction by introducing SEAL, a method that attributes predictions to meaningful molecular fragments, outperforming other methods in quantitative metrics and human-aligned interpretability.
Graph neural networks have demonstrated remarkable success in predicting molecular properties by leveraging the rich structural information encoded in molecular graphs. However, their black-box nature reduces interpretability, which limits trust in their predictions for important applications such as drug discovery and materials design. Furthermore, existing explanation techniques often fail to reliably quantify the contribution of individual atoms or substructures due to the entangled message-passing dynamics. We introduce SEAL (Substructure Explanation via Attribution Learning), a new interpretable graph neural network that attributes model predictions to meaningful molecular subgraphs. SEAL decomposes input graphs into chemically relevant fragments and estimates their causal influence on the output. The strong alignment between fragment contributions and model predictions is achieved by explicitly reducing inter-fragment message passing in our proposed model architecture. Extensive evaluations on synthetic benchmarks and real-world molecular datasets demonstrate that SEAL outperforms other explainability methods in both quantitative attribution metrics and human-aligned interpretability. A user study further confirms that SEAL provides more intuitive and trustworthy explanations to domain experts. By bridging the gap between predictive performance and interpretability, SEAL offers a promising direction for more transparent and actionable molecular modeling.