MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation

TL;DR

MAGE introduces a motif-based graph neural network explanation method that generates valid, human-understandable molecular substructure explanations by leveraging motif decomposition, attention mechanisms, and class-specific graph generation.

Contribution

This paper presents a novel motif-based explanation framework for GNNs that ensures validity and interpretability, addressing limitations of prior atom-based and embedding-based methods.

Findings

Effective in identifying meaningful molecular substructures

Produces valid and human-understandable explanations

Demonstrated on six real-world molecular datasets

Abstract

Graph Neural Networks (GNNs) have shown remarkable success in molecular tasks, yet their interpretability remains challenging. Traditional model-level explanation methods like XGNN and GNNInterpreter often fail to identify valid substructures like rings, leading to questionable interpretability. This limitation stems from XGNN's atom-by-atom approach and GNNInterpreter's reliance on average graph embeddings, which overlook the essential structural elements crucial for molecules. To address these gaps, we introduce an innovative \textbf{M}otif-b\textbf{A}sed \textbf{G}NN \textbf{E}xplainer (MAGE) that uses motifs as fundamental units for generating explanations. Our approach begins with extracting potential motifs through a motif decomposition technique. Then, we utilize an attention-based learning method to identify class-specific motifs. Finally, we employ a motif-based graph generator for each class to create molecular graph explanations based on these class-specific motifs. This novel method not only incorporates critical substructures into the explanations but also guarantees their validity, yielding results that are human-understandable. Our proposed method's effectiveness is demonstrated through quantitative and qualitative assessments conducted on six real-world molecular datasets.