mlsanityData to 7 Oct 2026

Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods

arXiv 2106.09078 ↗First posted 16 Jun 2021cs.LGcited by 36

Not on the map. Why?

Abstract (arXiv)

As Graph Neural Networks (GNNs) are increasingly being employed in critical real-world applications, several methods have been proposed in recent literature to explain the predictions of these models. However, there has been little to no work on systematically analyzing the reliability of these methods. Here, we introduce the first-ever theoretical analysis of the reliability of state-of-the-art GNN explanation methods. More specifically, we theoretically analyze the behavior of various state-of-the-art GNN explanation methods with respect to several desirable properties (e.g., faithfulness, stability, and fairness preservation) and establish upper bounds on the violation of these properties. We also empirically validate our theoretical results using extensive experimentation with nine real-world graph datasets. Our empirical results further shed light on several interesting insights about the behavior of state-of-the-art GNN explanation methods.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). Builds on 32 of its 55 references that are in the map. First posted on arXiv 16 Jun 2021.

Builds on

32 of 55 references.

References · 32

  1. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  2. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  3. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  4. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  5. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  6. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  7. 2019ERASER: A Benchmark to Evaluate Rationalized NLP Modelscited by 523
  8. 2019Graph Transformer Networkscited by 520
  9. 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 443
  10. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  11. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  12. 2018Regularisation of Neural Networks by Enforcing Lipschitz Continuitycited by 311
20 more
  1. 2018Learning to Explain: An Information-Theoretic Perspective on Model Interpretationcited by 248
  2. 2018Modeling polypharmacy side effects with graph convolutional networkscited by 237
  3. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  4. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 210
  5. 2019One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniquescited by 164
  6. 2019Explainability Techniques for Graph Convolutional Networkscited by 160
  7. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 152
  8. 2019Inherent Tradeoffs in Learning Fair Representationscited by 144
  9. 2020Higher-Order Explanations of Graph Neural Networks via Relevant Walkscited by 138
  10. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  11. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
  12. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 118
  13. 2020Building powerful and equivariant graph neural networks with structural message-passingcited by 95
  14. 2020Explaining the Explainer: A First Theoretical Analysis of LIMEcited by 89
  15. 2019Fairwashing: the risk of rationalizationcited by 81
  16. 2020Robust and Stable Black Box Explanationscited by 47
  17. 2021Towards the Unification and Robustness of Perturbation and Gradient Based Explanationscited by 47
  18. 2021To trust or not to trust an explanation: using LEAF to evaluate local linear XAI methodscited by 26
  19. 2020Contrastive Graph Neural Network Explanationcited by 20
  20. 2020A Performance-Explainability Framework to Benchmark Machine Learning Methods: Application to Multivariate Time Series Classifierscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 10; 2023: 9; 2024: 8; 2025: 7; 2026: 2.

36 papers.

Sort:

  1. 2022Evaluating Explainability for Graph Neural Networkscited by 85
  2. 2022GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networkscited by 57
  3. 2022Rethinking Stability for Attribution-based Explanationscited by 52
  4. 2023Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistencycited by 42
  5. 2022Explaining the Explainers in Graph Neural Networks: a Comparative Studycited by 34
  6. 2023Counterfactual Learning on Graphs: A Surveycited by 22
  7. 2024PowerGraph: A power grid benchmark dataset for graph neural networkscited by 19
  8. 2023Distill n' Explain: explaining graph neural networks using simple surrogatescited by 18
  9. 2023On the Robustness of Removal-Based Feature Attributionscited by 18
  10. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  11. 2023GInX-Eval: Towards In-Distribution Evaluation of Graph Neural Network Explanationscited by 9
  12. 2022L2XGNN: Learning to Explain Graph Neural Networkscited by 7
24 more
  1. 2022Towards Training GNNs using Explanation Directed Message Passingcited by 7
  2. 2022DT+GNN: A Fully Explainable Graph Neural Network using Decision Treescited by 6
  3. 2022A Sea of Words: An In-Depth Analysis of Anchors for Text Datacited by 6
  4. 2022Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functionscited by 6
  5. 2025Rethinking Explainability in the Era of Multimodal AIcited by 6
  6. 2024Explainable Graph Neural Networks Under Firecited by 5
  7. 2022ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention networkcited by 4
  8. 2023Graph AI in Medicinecited by 3
  9. 2024Iterative Graph Neural Network Enhancement via Frequent Subgraph Mining of Explanationscited by 3
  10. 2023Evaluating Link Prediction Explanations for Graph Neural Networkscited by 2
  11. 2026Quantifying Explanation Quality in Graph Neural Networks using Out-of-Distribution Generalizationcited by 2
  12. 2023Uncertainty Quantification for Local Model Explanations Without Model Accesscited by 1
  13. 2023GNNBleed: Inference Attacks to Unveil Private Edges in Graphs with Realistic Access to GNN Modelscited by 1
  14. 2024Introducing Diminutive Causal Structure into Graph Representation Learningcited by 1
  15. 2024On the Feasibility of Fidelity^- for Graph Pruningcited by 1
  16. 2025Explaining GNN Explanations with Edge Gradientscited by 1
  17. 2025Database Views as Explanations for Relational Deep Learningcited by 1
  18. 2024On Discprecncies between Perturbation Evaluations of Graph Neural Network Attributionscited by 0
  19. 2024Stability of Explainable Recommendationcited by 0
  20. 2024Vision Paper: Designing Graph Neural Networks in Compliance with the European Artificial Intelligence Actcited by 0
  21. 2025Causally Fair Node Classification on Non-IID Graph Datacited by 0
  22. 2025Enhancing Fairness in Autoencoders for Node-Level Graph Anomaly Detectioncited by 0
  23. 2025PruneGCRN: Minimizing and explaining spatio-temporal problems through node pruningcited by 0
  24. 2026General Semantic Knowledge Infusion for Spatio-Temporal Traffic Forecastingcited by 0