mlsanityData to 7 Oct 2026

GraphSVX: Shapley Value Explanations for Graph Neural Networks

arXiv 2104.10482 ↗First posted 18 Apr 2021cs.LGcited by 63

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) achieve significant performance for various learning tasks on geometric data due to the incorporation of graph structure into the learning of node representations, which renders their comprehension challenging. In this paper, we first propose a unified framework satisfied by most existing GNN explainers. Then, we introduce GraphSVX, a post hoc local model-agnostic explanation method specifically designed for GNNs. GraphSVX is a decomposition technique that captures the "fair" contribution of each feature and node towards the explained prediction by constructing a surrogate model on a perturbed dataset. It extends to graphs and ultimately provides as explanation the Shapley Values from game theory. Experiments on real-world and synthetic datasets demonstrate that GraphSVX achieves state-of-the-art performance compared to baseline models while presenting core theoretical and human-centric properties.

Key facts. Cited by 63 papers in the map (data through 7 Oct 2026). Builds on 28 of its 50 references that are in the map. First posted on arXiv 18 Apr 2021.

Builds on

28 of 50 references.

References · 28

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  5. 2017Inductive Representation Learning on Large Graphscited by 6,284
  6. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  7. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
  8. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  9. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  10. 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
  11. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  12. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
16 more
  1. 2018Link Prediction Based on Graph Neural Networkscited by 829
  2. 2015Convolutional Networks on Graphs for Learning Molecular Fingerprintscited by 751
  3. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  4. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  5. 2018Deep Learning on Graphs: A Surveycited by 393
  6. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 383
  7. 2016Top-down Neural Attention by Excitation Backpropcited by 318
  8. 2017Real Time Image Saliency for Black Box Classifierscited by 246
  9. 2020A Survey on the Explainability of Supervised Machine Learningcited by 225
  10. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  11. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 210
  12. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  13. 2019Explainability Techniques for Graph Convolutional Networkscited by 160
  14. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 152
  15. 2017Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to Stop Worrying and Love the Social and Behavioural Sciencescited by 84
  16. 2014Methods and Models for Interpretable Linear Classificationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 13; 2023: 10; 2024: 15; 2025: 13; 2026: 10.

63 papers.

Sort:

  1. 2022The Shapley Value in Machine Learningcited by 97
  2. 2022GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Gamescited by 42
  3. 2021Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networkscited by 34
  4. 2022GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networkscited by 34
  5. 2024Kolmogorov-Arnold Graph Neural Networkscited by 31
  6. 2023A Survey on Explainability of Graph Neural Networkscited by 28
  7. 2023DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networkscited by 27
  8. 2022GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendationscited by 22
  9. 2022A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protectioncited by 20
  10. 2022FlowX: Towards Explainable Graph Neural Networks via Message Flowscited by 20
  11. 2023Explanations of Black-Box Models based on Directional Feature Interactionscited by 15
  12. 2023A Comparative Study of Methods for Estimating Conditional Shapley Values and When to Use Themcited by 15
38 more
  1. 2023Towards Data-centric Graph Machine Learning: Review and Outlookcited by 15
  2. 2024GNNShap: Scalable and Accurate GNN Explanation using Shapley Valuescited by 12
  3. 2025Exact Computation of Any-Order Shapley Interactions for Graph Neural Networkscited by 12
  4. 2024Explaining Graph Neural Networks via Structure-aware Interaction Indexcited by 10
  5. 2024Comprehensible Artificial Intelligence on Knowledge Graphs: A surveycited by 8
  6. 2024Graph Neural Network Causal Explanation via Neural Causal Modelscited by 8
  7. 2022L2XGNN: Learning to Explain Graph Neural Networkscited by 7
  8. 2022DT+GNN: A Fully Explainable Graph Neural Network using Decision Treescited by 6
  9. 2022Explaining Preferences with Shapley Valuescited by 6
  10. 2023Efficient GNN Explanation via Learning Removal-based Attributioncited by 6
  11. 2025Recent Advances in Malware Detection: Graph Learning and Explainabilitycited by 6
  12. 2023Structural Explanations for Graph Neural Networks using HSICcited by 4
  13. 2024Towards Few-shot Self-explaining Graph Neural Networkscited by 4
  14. 2021Reliable Graph Neural Network Explanations Through Adversarial Trainingcited by 3
  15. 2022On the Limit of Explaining Black-box Temporal Graph Neural Networkscited by 3
  16. 2023Graph AI in Medicinecited by 3
  17. 2024Game-theoretic Counterfactual Explanation for Graph Neural Networkscited by 2
  18. 2024Generating Human Understandable Explanations for Node Embeddingscited by 2
  19. 2024A Comprehensive Study of Shapley Value in Data Analyticscited by 2
  20. 2025Z-REx: Human-Interpretable GNN Explanations for Real Estate Recommendationscited by 2
  21. 2025GnnXemplar: Exemplars to Explanations -- Natural Language Rules for Global GNN Interpretabilitycited by 2
  22. 2022PGX: A Multi-level GNN Explanation Framework Based on Separate Knowledge Distillation Processescited by 1
  23. 2023Counterfactual Graph Transformer for Traffic Flow Predictioncited by 1
  24. 2024Explanation-Preserving Augmentation for Semi-Supervised Graph Representation Learningcited by 1
  25. 2025Interpretability of Graph Neural Networks to Assess Effects of Global Change Drivers on Ecological Networkscited by 1
  26. 2025Towards Structurally Explainable Machine-Generated Text Detection: A Graph-Perspective Frameworkcited by 1
  27. 2025Statistical Test for Saliency Maps of Graph Neural Networks via Selective Inferencecited by 1
  28. 2025SliceGX: Layer-wise GNN Explanation with Model-slicingcited by 1
  29. 2022EiX-GNN : Concept-level eigencentrality explainer for graph neural networkscited by 0
  30. 2022ScoreCAM GNN: une explication optimale des r'eseaux profonds sur graphescited by 0
  31. 2023On the Interplay of Subset Selection and Informed Graph Neural Networkscited by 0
  32. 2024PAC Learnability under Explanation-Preserving Graph Perturbationscited by 0
  33. 2024LinkLogic: A New Method and Benchmark for Explainable Knowledge Graph Predictionscited by 0
  34. 2024Explaining Graph Neural Networks for Node Similarity on Graphscited by 0
  35. 2024PAGE: Parametric Generative Explainer for Graph Neural Networkcited by 0
  36. 2024MBExplainer: Multilevel bandit-based explanations for downstream models with augmented graph embeddingscited by 0
  37. 2025Interpretable Load Forecasting via Representation Learning of Geo-distributed Meteorological Factorscited by 0
  38. 2025Discovering the Precursors of Traffic Breakdowns Using Spatiotemporal Graph Attribution Networkscited by 0

50 most cited of 63 All 63 (JSON)