mlsanityData to 14 Oct 2026

Subgraph Concept Networks: Concept Levels in Graph Classification

arXiv 2604.18868 ↗First posted 20 Apr 2026cs.LGcited by 0

Not on the map. Why?

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.

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

18 of 30 references.

References · 18

  1. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
  2. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
  3. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  4. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
  5. 2019On Completeness-aware Concept-Based Explanations in Deep Neural Networkscited by 239
  6. 2020Graph Information Bottleneckcited by 168
  7. 2021ProtGNN: Towards Self-Explaining Graph Neural Networkscited by 96
  8. 2022Global Explainability of GNNs via Logic Combination of Learned Conceptscited by 65
  9. 2023Interpretable Neural-Symbolic Concept Reasoningcited by 57
  10. 2021Improving Subgraph Recognition with Variational Graph Information Bottleneckcited by 45
  11. 2021GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networkscited by 35
  12. 2022Explaining the Explainers in Graph Neural Networks: a Comparative Studycited by 35
6 more
  1. 2021Recognizing Predictive Substructures with Subgraph Information Bottleneckcited by 28
  2. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  3. 2024Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneckcited by 11
  4. 2024Unveiling Global Interactive Patterns across Graphs: Towards Interpretable Graph Neural Networkscited by 8
  5. 2025From GNNs to Trees: Multi-Granular Interpretability for Graph Neural Networkscited by 4
  6. 2023Everybody Needs a Little HELP: Explaining Graphs via Hierarchical Conceptscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Concept Graph Convolutions: Message Passing in the Concept Space
  2. 2026Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer
  3. 2024GNNAnatomy: Rethinking Model-Level Explanations for Graph Neural Networks
  4. 2023Distill n' Explain: explaining graph neural networks using simple surrogates
  5. 2021Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework
  6. 2022Toward Multiple Specialty Learners for Explaining GNNs via Online Knowledge Distillation
  7. 2023Towards Fine-Grained Explainability for Heterogeneous Graph Neural Network
  8. 2025NOCL: Node-Oriented Conceptualization LLM for Graph Tasks without Message Passing