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.
@article{arxiv.2604.18868,
title = {Subgraph Concept Networks: Concept Levels in Graph Classification},
author = {Lucie Charlotte Magister and Alexander Norcliffe and Iulia Duta and Pietro Lio},
journal= {arXiv preprint arXiv:2604.18868},
year = {2026}
}