RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation

TL;DR

This paper introduces RISE, a novel method for explaining 3D molecular GNNs by localizing explanations within a radius of influence around each node, improving interpretability by leveraging spatial and geometric features.

Contribution

The paper proposes a new explanation technique for 3D GNNs that localizes subgraph extraction based on a radius of influence, addressing challenges unique to 3D molecular graphs.

Findings

Enhances interpretability of 3D GNNs in molecular applications

Leverages spatial and geometric features for localized explanations

Aligns explanations with physical and structural dependencies

Abstract

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.