mlsanityData to 7 Oct 2026

GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarking

arXiv 2310.01794 ↗First posted 3 Oct 2023cs.LGcited by 11

Not on the map. Why?

Abstract (arXiv)

Numerous explainability methods have been proposed to shed light on the inner workings of GNNs. Despite the inclusion of empirical evaluations in all the proposed algorithms, the interrogative aspects of these evaluations lack diversity. As a result, various facets of explainability pertaining to GNNs, such as a comparative analysis of counterfactual reasoners, their stability to variational factors such as different GNN architectures, noise, stochasticity in non-convex loss surfaces, feasibility amidst domain constraints, and so forth, have yet to be formally investigated. Motivated by this need, we present a benchmarking study on perturbation-based explainability methods for GNNs, aiming to systematically evaluate and compare a wide range of explainability techniques. Among the key findings of our study, we identify the Pareto-optimal methods that exhibit superior efficacy and stability in the presence of noise. Nonetheless, our study reveals that all algorithms are affected by stability issues when faced with noisy data. Furthermore, we have established that the current generation of counterfactual explainers often fails to provide feasible recourses due to violations of topological constraints encoded by domain-specific considerations. Overall, this benchmarking study empowers stakeholders in the field of GNNs with a comprehensive understanding of the state-of-the-art explainability methods, potential research problems for further enhancement, and the implications of their application in real-world scenarios.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 48 of its 74 references that are in the map. First posted on arXiv 3 Oct 2023.

Builds on

48 of 74 references.

References · 48

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  6. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  7. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 702
  8. 2022DiGress: Discrete Denoising diffusion for graph generationcited by 503
  9. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  10. 2018GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Modelscited by 406
  11. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  12. 2021Do Transformers Really Perform Bad for Graph Representation?cited by 318
36 more
  1. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
  2. 2017A Survey of Machine Learning for Big Code and Naturalnesscited by 220
  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. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  6. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  7. 2019Explainability Techniques for Graph Convolutional Networkscited by 160
  8. 2020Higher-Order Explanations of Graph Neural Networks via Relevant Walkscited by 138
  9. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
  10. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 118
  11. 2022Evaluating Explainability for Graph Neural Networkscited by 85
  12. 2022Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoningcited by 78
  13. 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
  14. 2020GraphGen: A Scalable Approach to Domain-agnostic Labeled Graph Generationcited by 65
  15. 2022Global Explainability of GNNs via Logic Combination of Learned Conceptscited by 64
  16. 2022GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networkscited by 57
  17. 2020RelEx: A Model-Agnostic Relational Model Explainercited by 53
  18. 2021Knowledge-Preserving Incremental Social Event Detection via Heterogeneous GNNscited by 51
  19. 2022CLEAR: Generative Counterfactual Explanations on Graphscited by 48
  20. 2022GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Gamescited by 42
  21. 2021Counterfactual Graphs for Explainable Classification of Brain Networkscited by 33
  22. 2019Layerwise Relevance Visualization in Convolutional Text Graph Classifierscited by 32
  23. 2022Global Concept-Based Interpretability for Graph Neural Networks via Neuron Analysiscited by 32
  24. 2021GREED: A Neural Framework for Learning Graph Distance Functionscited by 31
  25. 2022Global Counterfactual Explainer for Graph Neural Networkscited by 30
  26. 2022A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challengescited by 30
  27. 2023A Survey on Explainability of Graph Neural Networkscited by 28
  28. 2022Unravelling the Performance of Physics-informed Graph Neural Networks for Dynamical Systemscited by 23
  29. 2019Understanding Isomorphism Bias in Graph Data Setscited by 22
  30. 2022Learning Articulated Rigid Body Dynamics with Lagrangian Graph Neural Networkcited by 22
  31. 2022Task-Agnostic Graph Explanationscited by 20
  32. 2022Enhancing the Inductive Biases of Graph Neural ODE for Modeling Dynamical Systemscited by 20
  33. 2023FRIGATE: Frugal Spatio-temporal Forecasting on Road Networkscited by 14
  34. 2022Learning the Dynamics of Particle-based Systems with Lagrangian Graph Neural Networkscited by 11
  35. 2021Event Detection on Dynamic Graphscited by 4
  36. 2023Robust Ante-hoc Graph Explainer using Bilevel Optimizationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 5; 2026: 2.

11 papers.

  1. 2024Faithful Interpretation for Graph Neural Networkscited by 3
  2. 2025Graph Counterfactual Explainable AI via Latent Space Traversalcited by 3
  3. 2024Game-theoretic Counterfactual Explanation for Graph Neural Networkscited by 2
  4. 2025GnnXemplar: Exemplars to Explanations -- Natural Language Rules for Global GNN Interpretabilitycited by 2
  5. 2024Towards Causal Classification: A Comprehensive Study on Graph Neural Networkscited by 1
  6. 2024Global Human-guided Counterfactual Explanations for Molecular Properties via Reinforcement Learningcited by 1
  7. 2025COMRECGC: Global Graph Counterfactual Explainer through Common Recoursecited by 1
  8. 2025ReconXF: Graph Reconstruction Attack via Public Feature Explanations on Privatized Node Features and Labelscited by 0
  9. 2025Explainable Graph Representation Learning via Graph Pattern Analysiscited by 0
  10. 2026Measuring What Matters: A Unified Evaluation Framework for GNN Explainabilitycited by 0
  11. 2026Automorphism-Induced Non-Canonicity in Top-k Explanations of Graph Neural Networkscited by 0