Concept Graph Convolutions: Message Passing in the Concept Space

• URL: http://arxiv.org/abs/2604.20082v1
• Date: Wed, 22 Apr 2026 00:57:06 GMT
• Title: Concept Graph Convolutions: Message Passing in the Concept Space
• Abstract summary: 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.
• Score: 14.872008669410098
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The trust in the predictions of Graph Neural Networks is limited by their opaque reasoning process. Prior methods have tried to explain graph networks via concept-based explanations extracted from the latent representations obtained after message passing. However, these explanations fall short of explaining the message passing process itself. To this aim, we propose the Concept Graph Convolution, the first graph convolution designed to operate on node-level concepts for improved interpretability. The proposed convolutional layer performs message passing on a combination of raw and concept representations using structural and attention-based edge weights. We also propose a pure variant of the convolution, only operating in the concept space. 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.

Related papers

• ConceptSeg-R1: Segment Any Concept via Meta-Reinforcement Learning [134.61875033137514]
  Recent progress in promptable segmentation has shifted visual perception from object-level localization toward concept-level understanding.<n>We formalize concept segmentation through a three-level taxonomy consisting of context-independent (CI), context-dependent (CD), and context-reasoning (CR) concepts.<n>We propose ConceptSeg-R1, a unified framework that reformulates concept segmentation as rule-induced concept grounding.
  arXiv  Detail & Related papers  (2026-05-19T18:35:38Z)
• Subgraph Concept Networks: Concept Levels in Graph Classification [52.68412528211993]
  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.
  arXiv  Detail & Related papers  (2026-04-20T21:44:05Z)
• 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)
• Revealing Combinatorial Reasoning of GNNs via Graph Concept Bottleneck Layer [28.886850252681754]
  We develop a graph concept layer that can be integrated into any GNN architectures.<n>The predicted concept scores are projected to class labels by the selected discriminative layer.<n>It enforces the sparse reasoning of GNNs' predictions to fit the soft logical rule over graph concepts.
  arXiv  Detail & Related papers  (2026-03-02T16:07:24Z)
• 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)
• Graph Concept Bottleneck Models [26.57626285653119]
  Concept Bottleneck Models (CBMs) provide explicit interpretations for deep neural networks through concepts.<n>We propose GraphCBMs: a new variant of CBM that facilitates concept relationships by constructing latent concept graphs.
  arXiv  Detail & Related papers  (2025-08-19T20:23:18Z)
• OmniPrism: Learning Disentangled Visual Concept for Image Generation [57.21097864811521]
  Creative visual concept generation often draws inspiration from specific concepts in a reference image to produce relevant outcomes.<n>We propose OmniPrism, a visual concept disentangling approach for creative image generation.<n>Our method learns disentangled concept representations guided by natural language and trains a diffusion model to incorporate these concepts.
  arXiv  Detail & Related papers  (2024-12-16T18:59:52Z)
• Concept Activation Regions: A Generalized Framework For Concept-Based Explanations [95.94432031144716]
  Existing methods assume that the examples illustrating a concept are mapped in a fixed direction of the deep neural network's latent space. In this work, we propose allowing concept examples to be scattered across different clusters in the DNN's latent space. This concept activation region (CAR) formalism yields global concept-based explanations and local concept-based feature importance.
  arXiv  Detail & Related papers  (2022-09-22T17:59:03Z)
• Concept Gradient: Concept-based Interpretation Without Linear Assumption [77.96338722483226]
  Concept Activation Vector (CAV) relies on learning a linear relation between some latent representation of a given model and concepts. We proposed Concept Gradient (CG), extending concept-based interpretation beyond linear concept functions. We demonstrated CG outperforms CAV in both toy examples and real world datasets.
  arXiv  Detail & Related papers  (2022-08-31T17:06:46Z)
• 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)

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.