The self-attention mechanism has been adopted in various popular message passing neural networks (MPNNs), enabling the model to adaptively control the amount of information that flows along the edges of the underlying graph. Such attention-based MPNNs (Att-GNNs) have also been used as a baseline for multiple studies on explainable AI (XAI) since attention has steadily been seen as natural model interpretations, while being a viewpoint that has already been popularized in other domains (e.g., natural language processing and computer vision). However, existing studies often use naive calculations to derive attribution scores from attention, undermining the potential of attention as interpretations for Att-GNNs. In our study, we aim to fill the gap between the widespread usage of Att-GNNs and their potential explainability via attention. To this end, we propose GAtt, edge attribution calculation method for self-attention MPNNs based on the computation tree, a rooted tree that reflects the computation process of the underlying model. Despite its simplicity, we empirically demonstrate the effectiveness of GAtt in three aspects of model explanation: faithfulness, explanation accuracy, and case studies by using both synthetic and real-world benchmark datasets. In all cases, the results demonstrate that GAtt greatly improves edge attribution scores, especially compared to the previous naive approach.

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 ([Formula: see text]), 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, [Formula: see text] selects embeddings of class-discriminative input graphs on the graph-level embedding space after clustering them. Then, [Formula: see text] 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 [Formula: see text] 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 [Formula: see text] and instance-level explanation methods, the robustness of [Formula: see text] to input data scarce environments, and the computational efficiency of the proposed prototype scoring function in [Formula: see text].

Aside the high performance of graph neural networks (GNNs), considerable attention has recently been paid to explanations of black-box deep learning models. Unlike most studies focusing on model explanations based on a specific graph instance, we propose Prototype-bAsed GNN-Explainer (PAGE), a novel model-level explanation method for graph-level classification that explains what the underlying model has learned by providing human-interpretable prototypes. Specifically, our method performs clustering on the embedding space of the underlying GNN model; extracts embeddings in each cluster; and discovers prototypes, which serve as model explanations, by estimating the maximum common subgraph (MCS) from the extracted embeddings. Experimental evaluation demonstrates that PAGE not only provides high-quality explanations but also outperforms the state-of-the-art model-level method in terms of consistency and faithfulness that are performance metrics for quantitative evaluations.