mlsanityData to 14 Oct 2026

A Survey on Explainability of Graph Neural Networks

arXiv 2306.01958 ↗First posted 2 Jun 2023cs.LG cs.AIcited by 29

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) are powerful graph-based deep-learning models that have gained significant attention and demonstrated remarkable performance in various domains, including natural language processing, drug discovery, and recommendation systems. However, combining feature information and combinatorial graph structures has led to complex non-linear GNN models. Consequently, this has increased the challenges of understanding the workings of GNNs and the underlying reasons behind their predictions. To address this, numerous explainability methods have been proposed to shed light on the inner mechanism of the GNNs. Explainable GNNs improve their security and enhance trust in their recommendations. This survey aims to provide a comprehensive overview of the existing explainability techniques for GNNs. We create a novel taxonomy and hierarchy to categorize these methods based on their objective and methodology. We also discuss the strengths, limitations, and application scenarios of each category. Furthermore, we highlight the key evaluation metrics and datasets commonly used to assess the explainability of GNNs. This survey aims to assist researchers and practitioners in understanding the existing landscape of explainability methods, identifying gaps, and fostering further advancements in interpretable graph-based machine learning.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). Builds on 83 of its 128 references that are in the map. First posted on arXiv 2 Jun 2023.

Builds on

83 of 128 references.

References · 83

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  5. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  6. 2019Simplifying Graph Convolutional Networkscited by 1,477
  7. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  8. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
  9. 2015Deep Learning and the Information Bottleneck Principlecited by 802
  10. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  11. 2017Learning Combinatorial Optimization Algorithms over Graphscited by 561
  12. 2020Parameterized Explainer for Graph Neural Networkcited by 426
38 more
  1. 2018T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Predictioncited by 401
  2. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
  3. 2021GFlowNet Foundationscited by 290
  4. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
  5. 2018Modeling polypharmacy side effects with graph convolutional networkscited by 237
  6. 2020A Survey on the Explainability of Supervised Machine Learningcited by 227
  7. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  8. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 211
  9. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  10. 2022Discovering Invariant Rationales for Graph Neural Networkscited by 188
  11. 2020Compositional Explanations of Neuronscited by 172
  12. 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
  13. 2019Understanding Attention and Generalization in Graph Neural Networkscited by 169
  14. 2019Explainability Techniques for Graph Convolutional Networkscited by 161
  15. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 153
  16. 2020Higher-Order Explanations of Graph Neural Networks via Relevant Walkscited by 138
  17. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
  18. 2021Human-Centered Explainable AI (XAI): From Algorithms to User Experiencescited by 123
  19. 2020Graph Information Bottleneck for Subgraph Recognitioncited by 119
  20. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 119
  21. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  22. 2020GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Mediacited by 109
  23. 2021Causal Attention for Interpretable and Generalizable Graph Classificationcited by 108
  24. 2021ProtGNN: Towards Self-Explaining Graph Neural Networkscited by 96
  25. 2022Debiasing Graph Neural Networks via Learning Disentangled Causal Substructurecited by 83
  26. 2022Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoningcited by 79
  27. 2021Towards Self-Explainable Graph Neural Networkcited by 75
  28. 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
  29. 2022Global Explainability of GNNs via Logic Combination of Learned Conceptscited by 65
  30. 2021GraphSVX: Shapley Value Explanations for Graph Neural Networkscited by 64
  31. 2022Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysiscited by 59
  32. 2020RelEx: A Model-Agnostic Relational Model Explainercited by 53
  33. 2022KerGNNs: Interpretable Graph Neural Networks with Graph Kernelscited by 50
  34. 2022CLEAR: Generative Counterfactual Explanations on Graphscited by 48
  35. 2021Logic Explained Networkscited by 45
  36. 2021Improving Subgraph Recognition with Variational Graph Information Bottleneckcited by 45
  37. 2018Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunitiescited by 43
  38. 2022GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Gamescited by 42

50 most cited of 83 All 83 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 11; 2025: 10; 2026: 6.

29 papers.

Sort:

By area:

  1. 2024Uncertainty in Graph Neural Networks: A Surveycited by 23
  2. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  3. 2024Reconsidering Faithfulness in Regular, Self-Explainable and Domain Invariant GNNscited by 16
  4. 2023GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarkingcited by 11
  5. 2024Explaining Graph Neural Networks via Structure-aware Interaction Indexcited by 11
  6. 2025Recent Advances in Malware Detection: Graph Learning and Explainabilitycited by 7
  7. 2023How Faithful are Self-Explainable GNNs?cited by 5
  8. 2024Explainable Graph Neural Networks Under Firecited by 5
  9. 2024Iterative Graph Neural Network Enhancement via Frequent Subgraph Mining of Explanationscited by 3
  10. 2024xAI-Drop: Don't Use What You Cannot Explaincited by 3
  11. 2025CausalAffect: Causal Discovery for Facial Affective Understandingcited by 3
  12. 2024Interpreting Temporal Graph Neural Networks with Koopman Theorycited by 2
17 more
  1. 2025Superposition in Graph Neural Networkscited by 2
  2. 2024Towards Understanding Sensitive and Decisive Patterns in Explainable AI: A Case Study of Model Interpretation in Geometric Deep Learningcited by 1
  3. 2024Disentangled and Self-Explainable Node Representation Learningcited by 1
  4. 2024MotifGPL: Motif-Enhanced Graph Prototype Learning for Deciphering Urban Social Segregationcited by 1
  5. 2025From Text to Graph: Leveraging Graph Neural Networks for Enhanced Explainability in NLPcited by 1
  6. 2025Towards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependenciescited by 1
  7. 2024Controllable Edge-Type-Specific Interpretation in Multi-Relational Graph Neural Networks for Drug Response Predictioncited by 0
  8. 2025NAEx: A Plug-and-Play Framework for Explaining Network Alignmentcited by 0
  9. 2025GDLNN: Marriage of Programming Language and Neural Networks for Accurate and Easy-to-Explain Graph Classificationcited by 0
  10. 2025ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule miningcited by 0
  11. 2025ATLAS: Adaptive Topology-based Learning at Scale for Homophilic and Heterophilic Graphscited by 0
  12. 2026BAED: a New Paradigm for Few-shot Graph Learning with Explanation in the Loopcited by 0
  13. 2026Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learningcited by 0
  14. 2026LLM Agents Make Collective Belief Dynamics Programmable: Challenges and Research Directionscited by 0
  15. 2026Communicating Credit Risk with Large Language Models: Evaluation of Explanations from Standard and Alternative Data-Based Modelscited by 0
  16. 2026Self-Explainable Multi-Label Graph Neural Network for Correlated Evidence Attributioncited by 0
  17. 2026HARMONIA: Interpretable Graph Learning through Mixtures of Neural Basescited by 0