mlsanityData to 7 Oct 2026

Layerwise Relevance Visualization in Convolutional Text Graph Classifiers

arXiv 1909.10911 ↗First posted 24 Sep 2019cs.CL cs.LGcited by 32

Not on the map. Why?

Abstract (arXiv)

Representations in the hidden layers of Deep Neural Networks (DNN) are often hard to interpret since it is difficult to project them into an interpretable domain. Graph Convolutional Networks (GCN) allow this projection, but existing explainability methods do not exploit this fact, i.e. do not focus their explanations on intermediate states. In this work, we present a novel method that traces and visualizes features that contribute to a classification decision in the visible and hidden layers of a GCN. Our method exposes hidden cross-layer dynamics in the input graph structure. We experimentally demonstrate that it yields meaningful layerwise explanations for a GCN sentence classifier.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 7; 2022: 8; 2023: 7; 2024: 5; 2025: 4; 2026: 1.

32 papers.

Sort:

  1. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
  2. 2021Benchmarking and Survey of Explanation Methods for Black Box Modelscited by 136
  3. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  4. 2021ProtGNN: Towards Self-Explaining Graph Neural Networkscited by 96
  5. 2021Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Futurecited by 67
  6. 2021A Survey on Graph-Based Deep Learning for Computational Histopathologycited by 41
  7. 2022GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networkscited by 34
  8. 2022Explaining the Explainers in Graph Neural Networks: a Comparative Studycited by 34
  9. 2021HistoCartography: A Toolkit for Graph Analytics in Digital Pathologycited by 20
  10. 2022A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protectioncited by 20
  11. 2023DEGREE: Decomposition Based Explanation For Graph Neural Networkscited by 18
  12. 2023Dynamic Causal Explanation Based Diffusion-Variational Graph Neural Network for Spatio-temporal Forecastingcited by 16
20 more
  1. 2024GNNShap: Scalable and Accurate GNN Explanation using Shapley Valuescited by 12
  2. 2023GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarkingcited by 11
  3. 2022Towards Explainable Motion Prediction using Heterogeneous Graph Representationscited by 10
  4. 2022Defending Against Backdoor Attack on Graph Nerual Network by Explainabilitycited by 9
  5. 2023Graph Neural Networks based Log Anomaly Detection and Explanationcited by 8
  6. 2024View-based Explanations for Graph Neural Networkscited by 8
  7. 2022L2XGNN: Learning to Explain Graph Neural Networkscited by 7
  8. 2022MEGAN: Multi-Explanation Graph Attention Networkcited by 7
  9. 2024GraphNarrator: Generating Textual Explanations for Graph Neural Networkscited by 7
  10. 2023ENGAGE: Explanation Guided Data Augmentation for Graph Representation Learningcited by 5
  11. 2024Explainable Graph Neural Networks Under Firecited by 5
  12. 2021Towards the Explanation of Graph Neural Networks in Digital Pathology with Information Flowscited by 4
  13. 2024Generating Robust Counterfactual Witnesses for Graph Neural Networkscited by 4
  14. 2023Semantic Interpretation and Validation of Graph Attention-based Explanations for GNN Modelscited by 3
  15. 2023KS-GNNExplainer: Global Model Interpretation Through Instance Explanations On Histopathology imagescited by 1
  16. 2025Database Views as Explanations for Relational Deep Learningcited by 1
  17. 2025Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Processcited by 0
  18. 2025ProteinPNet: Prototypical Part Networks for Concept Learning in Spatial Proteomicscited by 0
  19. 2025QGShap: Quantum Acceleration for Faithful GNN Explanationscited by 0
  20. 2026TACENR: Task-Agnostic Contrastive Explanations for Node Representationscited by 0