mlsanityData to 7 Oct 2026

Explainability Techniques for Graph Convolutional Networks

arXiv 1905.13686 ↗First posted 31 May 2019cs.LG cs.AI stat.MLcited by 160

Not on the map. Why?

Abstract (arXiv)

Graph Networks are used to make decisions in potentially complex scenarios but it is usually not obvious how or why they made them. In this work, we study the explainability of Graph Network decisions using two main classes of techniques, gradient-based and decomposition-based, on a toy dataset and a chemistry task. Our study sets the ground for future development as well as application to real-world problems.

Key facts. Cited by 160 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 24; 2022: 40; 2023: 36; 2024: 31; 2025: 17; 2026: 12.

160 papers.

Sort:

By area:

  1. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
  2. 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 260
  3. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  4. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 118
  5. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  6. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
  7. 2021ProtGNN: Towards Self-Explaining Graph Neural Networkscited by 96
  8. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  9. 2022Evaluating Explainability for Graph Neural Networkscited by 85
  10. 2022Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoningcited by 78
  11. 2021Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Futurecited by 67
  12. 2021GraphSVX: Shapley Value Explanations for Graph Neural Networkscited by 63
38 more
  1. 2022GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networkscited by 57
  2. 2022KerGNNs: Interpretable Graph Neural Networks with Graph Kernelscited by 50
  3. 2022GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Gamescited by 42
  4. 2021A Survey on Graph-Based Deep Learning for Computational Histopathologycited by 41
  5. 2021Sampling methods for efficient training of graph convolutional networks: A surveycited by 40
  6. 2021Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methodscited by 36
  7. 2021GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networkscited by 35
  8. 2022Reinforced Causal Explainer for Graph Neural Networkscited by 34
  9. 2022GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networkscited by 34
  10. 2022Explaining the Explainers in Graph Neural Networks: a Comparative Studycited by 34
  11. 2021MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networkscited by 32
  12. 2023Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalizationcited by 29
  13. 2023A Survey on Explainability of Graph Neural Networkscited by 28
  14. 2021Deep Ensembles from a Bayesian Perspectivecited by 27
  15. 2023DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networkscited by 27
  16. 2023TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discoverycited by 27
  17. 2022A Survey of Explainable Graph Neural Networks: Taxonomy and Evaluation Metricscited by 26
  18. 2022GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendationscited by 22
  19. 2023Counterfactual Learning on Graphs: A Surveycited by 22
  20. 2021Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsitycited by 20
  21. 2022A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protectioncited by 20
  22. 2022FlowX: Towards Explainable Graph Neural Networks via Message Flowscited by 20
  23. 2024EXGC: Bridging Efficiency and Explainability in Graph Condensationcited by 20
  24. 2024PowerGraph: A power grid benchmark dataset for graph neural networkscited by 19
  25. 2021Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networkscited by 18
  26. 2023DEGREE: Decomposition Based Explanation For Graph Neural Networkscited by 18
  27. 2023MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentationcited by 18
  28. 2024Graph Neural Network Explanations are Fragilecited by 18
  29. 2022Explainability in Graph Neural Networks: An Experimental Surveycited by 16
  30. 2022Private Graph Extraction via Feature Explanationscited by 16
  31. 2023CI-GNN: A Granger Causality-Inspired Graph Neural Network for Interpretable Brain Network-Based Psychiatric Diagnosiscited by 16
  32. 2023Dynamic Causal Explanation Based Diffusion-Variational Graph Neural Network for Spatio-temporal Forecastingcited by 16
  33. 2023Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networkscited by 16
  34. 2022On Structural Explanation of Bias in Graph Neural Networkscited by 15
  35. 2022Towards Prototype-Based Self-Explainable Graph Neural Networkcited by 14
  36. 2022Towards Faithful and Consistent Explanations for Graph Neural Networkscited by 13
  37. 2021Algorithmic Concept-based Explainable Reasoningcited by 12
  38. 2022Differentially Private Graph Classification with GNNscited by 12

50 most cited of 160 All 160 (JSON)