mlsanityData to 13 Oct 2026

Graph Neural Network Causal Explanation via Neural Causal Models

arXiv 2407.09378 ↗First posted 12 Jul 2024cs.LG cs.AI stat.MLcited by 9

Not on the map. Why?

Abstract (arXiv)

Graph neural network (GNN) explainers identify the important subgraph that ensures the prediction for a given graph. Until now, almost all GNN explainers are based on association, which is prone to spurious correlations. We propose name, a GNN causal explainer via causal inference. Our explainer is based on the observation that a graph often consists of a causal underlying subgraph. name includes three main steps: 1) It builds causal structure and the corresponding structural causal model (SCM) for a graph, which enables the cause-effect calculation among nodes. 2) Directly calculating the cause-effect in real-world graphs is computationally challenging. It is then enlightened by the recent neural causal model (NCM), a special type of SCM that is trainable, and design customized NCMs for GNNs. By training these GNN NCMs, the cause-effect can be easily calculated. 3) It uncovers the subgraph that causally explains the GNN predictions via the optimized GNN-NCMs. Evaluation results on multiple synthetic and real-world graphs validate that name significantly outperforms existing GNN explainers in exact groundtruth explanation identification

Key facts. Cited by 9 papers in the map (data through 13 Oct 2026). Builds on 36 of its 46 references that are in the map. First posted on arXiv 12 Jul 2024.

Builds on

36 of 46 references.

References · 36

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,318
  2. 2017Inductive Representation Learning on Large Graphscited by 6,303
  3. 2018How Powerful are Graph Neural Networks?cited by 4,373
  4. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,911
  5. 2020Parameterized Explainer for Graph Neural Networkcited by 425
  6. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
  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. 2019Explainability Techniques for Graph Convolutional Networkscited by 161
  11. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 153
  12. 2021Generative Causal Explanations for Graph Neural Networkscited by 124
24 more
  1. 2021Inducing Causal Structure for Interpretable Neural Networkscited by 108
  2. 2021Causal Attention for Interpretable and Generalizable Graph Classificationcited by 108
  3. 2019CXPlain: Causal Explanations for Model Interpretation under Uncertaintycited by 98
  4. 2021The Causal-Neural Connection: Expressiveness, Learnability, and Inferencecited by 97
  5. 2022Evaluating Explainability for Graph Neural Networkscited by 86
  6. 2022Debiasing Graph Neural Networks via Learning Disentangled Causal Substructurecited by 83
  7. 2021GraphSVX: Shapley Value Explanations for Graph Neural Networkscited by 64
  8. 2020Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbationcited by 57
  9. 2019Attacking Graph-based Classification via Manipulating the Graph Structurecited by 53
  10. 2020RelEx: A Model-Agnostic Relational Model Explainercited by 53
  11. 2022GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Gamescited by 42
  12. 2021Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networkscited by 35
  13. 2022Reinforced Causal Explainer for Graph Neural Networkscited by 34
  14. 2022GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networkscited by 34
  15. 2022OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networkscited by 33
  16. 2022Causal Explanations and XAIcited by 30
  17. 2023DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networkscited by 27
  18. 2021A Hard Label Black-box Adversarial Attack Against Graph Neural Networkscited by 26
  19. 2024Graph Neural Network Explanations are Fragilecited by 19
  20. 2023Distill n' Explain: explaining graph neural networks using simple surrogatescited by 18
  21. 2023DEGREE: Decomposition Based Explanation For Graph Neural Networkscited by 18
  22. 2019Saliency Methods for Explaining Adversarial Attackscited by 16
  23. 2023Turning Strengths into Weaknesses: A Certified Robustness Inspired Attack Framework against Graph Neural Networkscited by 11
  24. 2022Bandits for Structure Perturbation-based Black-box Attacks to Graph Neural Networks with Theoretical Guaranteescited by 9

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 4.

9 papers.

  1. 2025Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbationscited by 2
  2. 2025Causal Graph Neural Networks for Healthcarecited by 1
  3. 2026Structure-agnostic Causal Representation Learningcited by 1
  4. 2024Leveraging Local Structure for Improving Model Explanations: An Information Propagation Approachcited by 0
  5. 2025From Observations to Causations: A GNN-based Probabilistic Prediction Framework for Causal Discoverycited by 0
  6. 2025Neurocircuitry-Inspired Hierarchical Graph Causal Attention Networks for Explainable Depression Identificationcited by 0
  7. 2026CT-HEG: A Bidirectional, Timestamp-Attributed Event Graph for ICU In-Hospital Mortality Prediction - An Architectural Ablation Studycited by 0
  8. 2026Causal Memory Policy: Making Memory Utility Identifiable by Intervening on Retrievalcited by 0
  9. 2026Reasoning Models Are Accurate but Unsound on Identificationcited by 0