mlsanityData to 7 Oct 2026

Evaluating Explainability for Graph Neural Networks

arXiv 2208.09339 ↗First posted 19 Aug 2022cs.LG cs.AIcited by 85

Not on the map. Why?

Abstract (arXiv)

As post hoc explanations are increasingly used to understand the behavior of graph neural networks (GNNs), it becomes crucial to evaluate the quality and reliability of GNN explanations. However, assessing the quality of GNN explanations is challenging as existing graph datasets have no or unreliable ground-truth explanations for a given task. Here, we introduce a synthetic graph data generator, ShapeGGen, which can generate a variety of benchmark datasets (e.g., varying graph sizes, degree distributions, homophilic vs. heterophilic graphs) accompanied by ground-truth explanations. Further, the flexibility to generate diverse synthetic datasets and corresponding ground-truth explanations allows us to mimic the data generated by various real-world applications. We include ShapeGGen and several real-world graph datasets into an open-source graph explainability library, GraphXAI. In addition to synthetic and real-world graph datasets with ground-truth explanations, GraphXAI provides data loaders, data processing functions, visualizers, GNN model implementations, and evaluation metrics to benchmark the performance of GNN explainability methods.

Key facts. Cited by 85 papers in the map (data through 7 Oct 2026). Builds on 28 of its 54 references that are in the map. First posted on arXiv 19 Aug 2022.

Builds on

28 of 54 references.

References · 28

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2018How Powerful are Graph Neural Networks?cited by 4,355
  3. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  4. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  5. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  6. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  7. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  8. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  9. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  10. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  11. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 280
  12. 2021Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Developmentcited by 258
16 more
  1. 2019Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networkscited by 241
  2. 2018Modeling polypharmacy side effects with graph convolutional networkscited by 237
  3. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 210
  4. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  5. 2019Explainability Techniques for Graph Convolutional Networkscited by 160
  6. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 152
  7. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  8. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 118
  9. 2020Node Similarity Preserving Graph Convolutional Networkscited by 112
  10. 2021DIG: A Turnkey Library for Diving into Graph Deep Learning Researchcited by 76
  11. 2020A Large-Scale Database for Graph Representation Learningcited by 54
  12. 2021Graph Robustness Benchmark: Benchmarking the Adversarial Robustness of Graph Machine Learningcited by 44
  13. 2020Network Medicine Framework for Identifying Drug Repurposing Opportunities for COVID-19cited by 38
  14. 2021Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methodscited by 36
  15. 2021Benchmarking the Combinatorial Generalizability of Complex Query Answering on Knowledge Graphscited by 21
  16. 2020Contrastive Graph Neural Network Explanationcited by 20

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 20; 2024: 22; 2025: 23; 2026: 16.

85 papers.

Sort:

By area:

  1. 2023Similarity of Neural Network Models: A Survey of Functional and Representational Measurescited by 128
  2. 2022Global Explainability of GNNs via Logic Combination of Learned Conceptscited by 64
  3. 2023Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistencycited by 42
  4. 2022Explaining the Explainers in Graph Neural Networks: a Comparative Studycited by 34
  5. 2024How Do Large Language Models Understand Graph Patterns? A Benchmark for Graph Pattern Comprehensioncited by 30
  6. 2023Counterfactual Learning on Graphs: A Surveycited by 22
  7. 2024PowerGraph: A power grid benchmark dataset for graph neural networkscited by 19
  8. 2023Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networkscited by 16
  9. 2025No Metric to Rule Them All: Toward Principled Evaluations of Graph-Learning Datasetscited by 16
  10. 2024Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNscited by 14
  11. 2025Exact Computation of Any-Order Shapley Interactions for Graph Neural Networkscited by 12
  12. 2022On the Probability of Necessity and Sufficiency of Explaining Graph Neural Networks: A Lower Bound Optimization Approachcited by 11
38 more
  1. 2023GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarkingcited by 11
  2. 2024Explaining Graph Neural Networks via Structure-aware Interaction Indexcited by 10
  3. 2025Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspectivecited by 10
  4. 2023GInX-Eval: Towards In-Distribution Evaluation of Graph Neural Network Explanationscited by 9
  5. 2023Exploring Causal Learning through Graph Neural Networks: An In-depth Reviewcited by 8
  6. 2024Graph Neural Network Causal Explanation via Neural Causal Modelscited by 8
  7. 2022Towards Training GNNs using Explanation Directed Message Passingcited by 7
  8. 2024A Self-Explainable Heterogeneous GNN for Relational Deep Learningcited by 7
  9. 2023Saliency-Bench: A Comprehensive Benchmark for Evaluating Visual Explanationscited by 6
  10. 2025Rethinking Explainability in the Era of Multimodal AIcited by 6
  11. 2023How Faithful are Self-Explainable GNNs?cited by 5
  12. 2024Explainable Graph Neural Networks Under Firecited by 5
  13. 2024The FIX Benchmark: Extracting Features Interpretable to eXpertscited by 5
  14. 2023Robust Ante-hoc Graph Explainer using Bilevel Optimizationcited by 4
  15. 2023Generative Explanations for Graph Neural Network: Methods and Evaluationscited by 4
  16. 2025Interpretable Retinal Disease Prediction Using Biology-Informed Heterogeneous Graph Representationscited by 4
  17. 2025B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Datacited by 4
  18. 2023AttributionLab: Faithfulness of Feature Attribution Under Controllable Environmentscited by 3
  19. 2023Graph AI in Medicinecited by 3
  20. 2024Iterative Graph Neural Network Enhancement via Frequent Subgraph Mining of Explanationscited by 3
  21. 2026GNN Explanations that do not Explain and How to find Themcited by 3
  22. 2026Explainable AI for Jet Tagging: A Comparative Study of GNNExplainer, GNNShap, and GradCAM for Jet Tagging in the Lund Jet Planecited by 3
  23. 2023Unstructured and structured data: Can we have the best of both worlds with large language models?cited by 2
  24. 2023Evaluating Link Prediction Explanations for Graph Neural Networkscited by 2
  25. 2024Generating Human Understandable Explanations for Node Embeddingscited by 2
  26. 2024Revisiting FunnyBirds evaluation framework for prototypical parts networkscited by 2
  27. 2024DRExplainer: Quantifiable Interpretability in Drug Response Prediction with Directed Graph Convolutional Networkcited by 2
  28. 2024Interpreting Temporal Graph Neural Networks with Koopman Theorycited by 2
  29. 2024Machines and Mathematical Mutations: Using GNNs to Characterize Quiver Mutation Classescited by 2
  30. 2025Is Your Explanation Reliable: Confidence-Aware Explanation on Graph Neural Networkscited by 2
  31. 2026ATEX-CF: Attack-Informed Counterfactual Explanations for Graph Neural Networkscited by 2
  32. 2023Advancing Biomedicine with Graph Representation Learning: Recent Progress, Challenges, and Future Directionscited by 1
  33. 2023Is Task-Agnostic Explainable AI a Myth?cited by 1
  34. 2023A Unified Pre-training and Adaptation Framework for Combinatorial Optimization on Graphscited by 1
  35. 2023Explainability-Based Adversarial Attack on Graphs Through Edge Perturbationcited by 1
  36. 2024Discovering robust biomarkers of psychiatric disorders from resting-state functional MRI via graph neural networks: A systematic reviewcited by 1
  37. 2024Towards Understanding Sensitive and Decisive Patterns in Explainable AI: A Case Study of Model Interpretation in Geometric Deep Learningcited by 1
  38. 2024Explaining Hypergraph Neural Networks: From Local Explanations to Global Conceptscited by 1

50 most cited of 85 All 85 (JSON)