PAGE: Prototype-Based Model-Level Explanations for Graph Neural Networks
This addresses the need for more concise and comprehensive explanations in GNNs, which is important for users in fields like bioinformatics or social network analysis, though it is incremental as it builds on existing explanation methods.
The paper tackles the problem of explaining graph neural networks (GNNs) for graph classification by proposing PAGE, a model-level explanation method that discovers human-interpretable prototype graphs, and demonstrates that it outperforms the state-of-the-art model-level explanation method across six datasets.
Aside from graph neural networks (GNNs) attracting significant attention as a powerful framework revolutionizing graph representation learning, there has been an increasing demand for explaining GNN models. Although various explanation methods for GNNs have been developed, most studies have focused on instance-level explanations, which produce explanations tailored to a given graph instance. In our study, we propose Prototype-bAsed GNN-Explainer (PAGE), a novel model-level GNN explanation method that explains what the underlying GNN model has learned for graph classification by discovering human-interpretable prototype graphs. Our method produces explanations for a given class, thus being capable of offering more concise and comprehensive explanations than those of instance-level explanations. First, PAGE selects embeddings of class-discriminative input graphs on the graph-level embedding space after clustering them. Then, PAGE discovers a common subgraph pattern by iteratively searching for high matching node tuples using node-level embeddings via a prototype scoring function, thereby yielding a prototype graph as our explanation. Using six graph classification datasets, we demonstrate that PAGE qualitatively and quantitatively outperforms the state-of-the-art model-level explanation method. We also carry out systematic experimental studies by demonstrating the relationship between PAGE and instance-level explanation methods, the robustness of PAGE to input data scarce environments, and the computational efficiency of the proposed prototype scoring function in PAGE.