mlsanityData to 7 Oct 2026

GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networks

arXiv 2209.07924 ↗First posted 15 Sep 2022cs.LG cs.AIcited by 34

Not on the map. Why?

Abstract (arXiv)

Recently, Graph Neural Networks (GNNs) have significantly advanced the performance of machine learning tasks on graphs. However, this technological breakthrough makes people wonder: how does a GNN make such decisions, and can we trust its prediction with high confidence? When it comes to some critical fields, such as biomedicine, where making wrong decisions can have severe consequences, it is crucial to interpret the inner working mechanisms of GNNs before applying them. In this paper, we propose a model-agnostic model-level explanation method for different GNNs that follow the message passing scheme, GNNInterpreter, to explain the high-level decision-making process of the GNN model. More specifically, GNNInterpreter learns a probabilistic generative graph distribution that produces the most discriminative graph pattern the GNN tries to detect when making a certain prediction by optimizing a novel objective function specifically designed for the model-level explanation for GNNs. Compared to existing works, GNNInterpreter is more flexible and computationally efficient in generating explanation graphs with different types of node and edge features, without introducing another blackbox or requiring manually specified domain-specific rules. In addition, the experimental studies conducted on four different datasets demonstrate that the explanation graphs generated by GNNInterpreter match the desired graph pattern if the model is ideal; otherwise, potential model pitfalls can be revealed by the explanation. The official implementation can be found at https://github.com/yolandalalala/GNNInterpreter.

Key facts. Cited by 34 papers in the map (data through 7 Oct 2026). Builds on 28 of its 43 references that are in the map. First posted on arXiv 15 Sep 2022.

Builds on

28 of 43 references.

References · 28

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  6. 2018How Powerful are Graph Neural Networks?cited by 4,355
  7. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  8. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  9. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  10. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  11. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,135
  12. 2018Link Prediction Based on Graph Neural Networkscited by 829
16 more
  1. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  2. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  3. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  4. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  5. 2016Top-down Neural Attention by Excitation Backpropcited by 318
  6. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
  7. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  8. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 210
  9. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  10. 2016Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layerscited by 197
  11. 2019Explainability Techniques for Graph Convolutional Networkscited by 160
  12. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
  13. 2021GraphSVX: Shapley Value Explanations for Graph Neural Networkscited by 63
  14. 2022OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networkscited by 33
  15. 2019Layerwise Relevance Visualization in Convolutional Text Graph Classifierscited by 32
  16. 2022MotifExplainer: a Motif-based Graph Neural Network Explainercited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 8; 2024: 12; 2025: 10; 2026: 3.

34 papers.

Sort:

By area:

  1. 2022Explaining the Explainers in Graph Neural Networks: a Comparative Studycited by 34
  2. 2023A Survey on Explainability of Graph Neural Networkscited by 28
  3. 2023TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discoverycited by 27
  4. 2024Graph Neural Network Explanations are Fragilecited by 18
  5. 2023Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networkscited by 16
  6. 2025No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasetscited by 16
  7. 2024Explaining Graph Neural Networks via Structure-aware Interaction Indexcited by 10
  8. 2023D4Explainer: In-Distribution GNN Explanations via Discrete Denoising Diffusioncited by 9
  9. 2024Graph Neural Network Causal Explanation via Neural Causal Modelscited by 8
  10. 2024MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generationcited by 7
  11. 2024A Self-Explainable Heterogeneous GNN for Relational Deep Learningcited by 7
  12. 2025Recent Advances in Malware Detection: Graph Learning and Explainabilitycited by 6
22 more
  1. 2023Generative Explanations for Graph Neural Network: Methods and Evaluationscited by 4
  2. 2024Towards Few-shot Self-explaining Graph Neural Networkscited by 4
  3. 2024xAI-Drop: Don't Use What You Cannot Explaincited by 3
  4. 2023Unstructured and structured data: Can we have the best of both worlds with large language models?cited by 2
  5. 2023Everybody Needs a Little HELP: Explaining Graphs via Hierarchical Conceptscited by 2
  6. 2024Interpreting Temporal Graph Neural Networks with Koopman Theorycited by 2
  7. 2025GnnXemplar: Exemplars to Explanations -- Natural Language Rules for Global GNN Interpretabilitycited by 2
  8. 2023KS-GNNExplainer: Global Model Interpretation Through Instance Explanations On Histopathology imagescited by 1
  9. 2024Discovering robust biomarkers of psychiatric disorders from resting-state functional MRI via graph neural networks: A systematic reviewcited by 1
  10. 2025Towards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependenciescited by 1
  11. 2026Relevant Walk Search for Explaining Graph Neural Networkscited by 1
  12. 2024PAC Learnability under Explanation-Preserving Graph Perturbationscited by 0
  13. 2024SES: Bridging the Gap Between Explainability and Prediction of Graph Neural Networkscited by 0
  14. 2024PAGE: Parametric Generative Explainer for Graph Neural Networkcited by 0
  15. 2025GIN-Graph: A Generative Interpretation Network for Model-Level Explanation of Graph Neural Networkscited by 0
  16. 2025Model-Level GNN Explanations via Rule-to-Graph Readout for Logit Reconstructioncited by 0
  17. 2025LogicXGNN: Grounded Logical Rules for Explaining Graph Neural Networkscited by 0
  18. 2025How do Probabilistic Graphical Models and Graph Neural Networks Look at Network Data?cited by 0
  19. 2025Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Processcited by 0
  20. 2025ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule miningcited by 0
  21. 2026AIMing for Standardised Explainability Evaluation in GNNs: A Framework and Case Study on Graph Kernel Networkscited by 0
  22. 2026Towards Faithful Graph Explanations with Synergistic Edge Effects via Granular Ballscited by 0