mlsanityData to 7 Oct 2026

Generative Explanations for Graph Neural Network: Methods and Evaluations

arXiv 2311.05764 ↗First posted 9 Nov 2023cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) achieve state-of-the-art performance in various graph-related tasks. However, the black-box nature often limits their interpretability and trustworthiness. Numerous explainability methods have been proposed to uncover the decision-making logic of GNNs, by generating underlying explanatory substructures. In this paper, we conduct a comprehensive review of the existing explanation methods for GNNs from the perspective of graph generation. Specifically, we propose a unified optimization objective for generative explanation methods, comprising two sub-objectives: Attribution and Information constraints. We further demonstrate their specific manifestations in various generative model architectures and different explanation scenarios. With the unified objective of the explanation problem, we reveal the shared characteristics and distinctions among current methods, laying the foundation for future methodological advancements. Empirical results demonstrate the advantages and limitations of different explainability approaches in terms of explanation performance, efficiency, and generalizability.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 45 of its 54 references that are in the map. First posted on arXiv 9 Nov 2023.

Builds on

45 of 54 references.

References · 45

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  4. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  5. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  6. 2016Variational Graph Auto-Encoderscited by 1,373
  7. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  8. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  9. 2019Graph Neural Networks for Social Recommendationcited by 711
  10. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 503
  11. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 500
  12. 2020Parameterized Explainer for Graph Neural Networkcited by 423
33 more
  1. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 384
  2. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  3. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
  4. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  5. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 210
  6. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  7. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  8. 2019Explainability Techniques for Graph Convolutional Networkscited by 160
  9. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 152
  10. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
  11. 2020Graph Information Bottleneck for Subgraph Recognitioncited by 119
  12. 2020Drug discovery with explainable artificial intelligencecited by 118
  13. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  14. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  15. 2022Evaluating Explainability for Graph Neural Networkscited by 85
  16. 2020Molecular graph generation with Graph Neural Networkscited by 79
  17. 2022Diffusion Models for Counterfactual Explanationscited by 79
  18. 2021A Review on Graph Neural Network Methods in Financial Applicationscited by 77
  19. 2022Diffusion Models for Graphs Benefit From Discrete State Spacescited by 69
  20. 2022Global Explainability of GNNs via Logic Combination of Learned Conceptscited by 64
  21. 2022GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networkscited by 57
  22. 2022CLEAR: Generative Counterfactual Explanations on Graphscited by 48
  23. 2020Model extraction from counterfactual explanationscited by 46
  24. 2022Reinforced Causal Explainer for Graph Neural Networkscited by 34
  25. 2022GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networkscited by 34
  26. 2022OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networkscited by 33
  27. 2022A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challengescited by 30
  28. 2023DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networkscited by 27
  29. 2022A Survey of Explainable Graph Neural Networks: Taxonomy and Evaluation Metricscited by 26
  30. 2022A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protectioncited by 20
  31. 2023D4Explainer: In-Distribution GNN Explanations via Discrete Denoising Diffusioncited by 9
  32. 2021Counterfactual Explanation with Multi-Agent Reinforcement Learning for Drug Target Predictioncited by 8
  33. 2022GANExplainer: GAN-based Graph Neural Networks Explainercited by 2

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 2; 2025: 1.

4 papers.

  1. 2024Explaining Graph Neural Networks via Structure-aware Interaction Indexcited by 10
  2. 2023Exploring Causal Learning through Graph Neural Networks: An In-depth Reviewcited by 8
  3. 2024Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networkscited by 3
  4. 2025NAEx: A Plug-and-Play Framework for Explaining Network Alignmentcited by 0