# Subgraph Concept Networks: Concept Levels in Graph Classification

arXiv: https://arxiv.org/abs/2604.18868 · HTML: https://mlsanity.com/paper/2604.18868/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 30 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 18 of 18)

- [Hierarchical Graph Representation Learning with Differentiable Pooling](https://mlsanity.com/paper/1806.08804/) (2018)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [TUDataset: A collection of benchmark datasets for learning with graphs](https://mlsanity.com/paper/2007.08663/) (2020)
- [On Completeness-aware Concept-Based Explanations in Deep Neural Networks](https://mlsanity.com/paper/1910.07969/) (2019)
- [Graph Information Bottleneck](https://mlsanity.com/paper/2010.12811/) (2020)
- [ProtGNN: Towards Self-Explaining Graph Neural Networks](https://mlsanity.com/paper/2112.00911/) (2021)
- [Global Explainability of GNNs via Logic Combination of Learned Concepts](https://mlsanity.com/paper/2210.07147/) (2022)
- [Interpretable Neural-Symbolic Concept Reasoning](https://mlsanity.com/paper/2304.14068/) (2023)
- [Improving Subgraph Recognition with Variational Graph Information Bottleneck](https://mlsanity.com/paper/2112.09899/) (2021)
- [GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks](https://mlsanity.com/paper/2107.11889/) (2021)
- [Explaining the Explainers in Graph Neural Networks: a Comparative Study](https://mlsanity.com/paper/2210.15304/) (2022)
- [Recognizing Predictive Substructures with Subgraph Information Bottleneck](https://mlsanity.com/paper/2103.11155/) (2021)
- [A Comprehensive Survey on Self-Interpretable Neural Networks](https://mlsanity.com/paper/2501.15638/) (2025)
- [Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck](https://mlsanity.com/paper/2412.15589/) (2024)
- [Unveiling Global Interactive Patterns across Graphs: Towards Interpretable Graph Neural Networks](https://mlsanity.com/paper/2407.01979/) (2024)
- [From GNNs to Trees: Multi-Granular Interpretability for Graph Neural Networks](https://mlsanity.com/paper/2505.00364/) (2025)
- [Everybody Needs a Little HELP: Explaining Graphs via Hierarchical Concepts](https://mlsanity.com/paper/2311.15112/) (2023)

## Abstract (arXiv)

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.