Subgraph Concept Networks: Concept Levels in Graph Classification

• URL: http://arxiv.org/abs/2604.18868v1
• Date: Mon, 20 Apr 2026 21:44:05 GMT
• Title: Subgraph Concept Networks: Concept Levels in Graph Classification
• Abstract summary: Subgraph Concept Network is first graph neural network architecture that distils subgraph and graph-level concepts.<n>It achieves this by performing soft clustering on node concept embeddings to derive subgraph and graph-level concepts.<n>Our results show that the Subgraph Concept Network allows to obtain competitive model accuracy, while discovering meaningful concepts at different levels of the network.
• Score: 52.68412528211993
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Concept Graph Convolutions: Message Passing in the Concept Space [14.872008669410098]
  We propose the first graph convolution designed to operate on node-level concepts for improved interpretability.<n>The proposed convolutional layer performs message passing on a combination of raw and concept representations using structural and attention-based edge weights.<n>Our results show that the Concept Graph Convolution allows to obtain competitive task accuracy, while enabling an increased insight into the evolution of concepts across convolutional steps.
  arXiv  Detail & Related papers  (2026-04-22T00:57:06Z)
• Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learning [10.84756768352255]
  We introduce Graph Concept Bottleneck (GCB) as a new paradigm for self-explainable text-attributed graph learning.<n>GCB maps graphs into a subspace, concept bottleneck, where each concept is a meaningful phrase.<n>We empirically show that GCB achieves intrinsic interpretability with accuracy on par with black-box Graph Neural Networks.
  arXiv  Detail & Related papers  (2026-04-13T19:26:36Z)
• FaCT: Faithful Concept Traces for Explaining Neural Network Decisions [56.796533084868884]
  Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge.<n>We put emphasis on the faithfulness of concept-based explanations and propose a new model with model-inherent mechanistic concept-explanations.<n>Our concepts are shared across classes and, from any layer, their contribution to the logit and their input-visualization can be faithfully traced.
  arXiv  Detail & Related papers  (2025-10-29T13:35:46Z)
• RAW-Explainer: Post-hoc Explanations of Graph Neural Networks on Knowledge Graphs [0.0]
  RAW-Explainer is a novel framework designed to generate connected, concise, and thus interpretable subgraph explanations for link prediction.<n>Unlike existing methods tailored to knowledge graphs, our approach employs a neural network to parameterize the explanation generation process.<n>Our approach strikes a balance between explanation quality and computational efficiency.
  arXiv  Detail & Related papers  (2025-06-14T15:55:17Z)
• ResolvNet: A Graph Convolutional Network with multi-scale Consistency [47.98039061491647]
  We introduce the concept of multi-scale consistency. At the graph-level, multi-scale consistency refers to the fact that distinct graphs describing the same object at different resolutions should be assigned similar feature vectors. We introduce ResolvNet, a flexible graph neural network based on the mathematical concept of resolvents.
  arXiv  Detail & Related papers  (2023-09-30T16:46:45Z)
• Encoding Concepts in Graph Neural Networks [6.129235861306906]
  We introduce the Concept Module, the first differentiable concept-discovery approach for graph networks. The proposed approach makes graph networks explainable by design by first discovering graph concepts and then using these to solve the task. Our results demonstrate that this approach allows graph networks to attain model accuracy comparable with their equivalent vanilla versions.
  arXiv  Detail & Related papers  (2022-07-27T15:34:14Z)
• Reasoning Graph Networks for Kinship Verification: from Star-shaped to Hierarchical [85.0376670244522]
  We investigate the problem of facial kinship verification by learning hierarchical reasoning graph networks. We develop a Star-shaped Reasoning Graph Network (S-RGN) to exploit more powerful and flexible capacity. We also develop a Hierarchical Reasoning Graph Network (H-RGN) to exploit more powerful and flexible capacity.
  arXiv  Detail & Related papers  (2021-09-06T03:16:56Z)
• Spectral Embedding of Graph Networks [76.27138343125985]
  We introduce an unsupervised graph embedding that trades off local node similarity and connectivity, and global structure. The embedding is based on a generalized graph Laplacian, whose eigenvectors compactly capture both network structure and neighborhood proximity in a single representation.
  arXiv  Detail & Related papers  (2020-09-30T04:59:10Z)
• Progressive Graph Convolutional Networks for Semi-Supervised Node Classification [97.14064057840089]
  Graph convolutional networks have been successful in addressing graph-based tasks such as semi-supervised node classification. We propose a method to automatically build compact and task-specific graph convolutional networks.
  arXiv  Detail & Related papers  (2020-03-27T08:32:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.