RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation
This addresses the need for reliable and transparent insights in scientific applications like molecular learning, though it appears incremental as it adapts explanation methods from 2D to 3D GNNs.
The paper tackles the limited interpretability of 3D Geometric Graph Neural Networks (GNNs) for molecular data by introducing a novel explanation method that localizes explanations to the immediate neighborhood of each node using a radius of influence, enhancing interpretability and aligning with physical dependencies in 3D graphs.
3D Geometric Graph Neural Networks (GNNs) have emerged as transformative tools for modeling molecular data. Despite their predictive power, these models often suffer from limited interpretability, raising concerns for scientific applications that require reliable and transparent insights. While existing methods have primarily focused on explaining molecular substructures in 2D GNNs, the transition to 3D GNNs introduces unique challenges, such as handling the implicit dense edge structures created by a cut-off radius. To tackle this, we introduce a novel explanation method specifically designed for 3D GNNs, which localizes the explanation to the immediate neighborhood of each node within the 3D space. Each node is assigned an radius of influence, defining the localized region within which message passing captures spatial and structural interactions crucial for the model's predictions. This method leverages the spatial and geometric characteristics inherent in 3D graphs. By constraining the subgraph to a localized radius of influence, the approach not only enhances interpretability but also aligns with the physical and structural dependencies typical of 3D graph applications, such as molecular learning.