Subgraph Concept Networks: Concept Levels in Graph Classification
For graph classification tasks, this work addresses the opacity of GNN reasoning by enabling concept-based explanations at subgraph and graph levels, which prior work could not achieve.
The authors propose Subgraph Concept Networks, the first GNN architecture that distills subgraph and graph-level concepts via soft clustering on node concept embeddings, achieving competitive accuracy while providing interpretable multi-level concepts.
The reasoning process of Graph Neural Networks is complex and considered opaque, limiting trust in their predictions. To alleviate this issue, prior work has proposed concept-based explanations, extracted from clusters in the model's node embeddings. However, a limitation of concept-based explanations is that they only explain the node embedding space and are obscured by pooling in graph classification. To mitigate this issue and provide a deeper level of understanding, we propose the Subgraph Concept Network. The Subgraph Concept Network is the first graph neural network architecture that distils subgraph and graph-level concepts. It achieves this by performing soft clustering on node concept embeddings to derive subgraph and graph-level concepts. Our results show that the Subgraph Concept Network allows to obtain competitive model accuracy, while discovering meaningful concepts at different levels of the network.