# Graph Neural Network Causal Explanation via Neural Causal Models

arXiv: https://arxiv.org/abs/2407.09378 · HTML: https://mlsanity.com/paper/2407.09378/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 46 references that are in the map.
- First posted on arXiv 12 Jul 2024.

## Builds on (most cited first, 30 of 36)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Parameterized Explainer for Graph Neural Network](https://mlsanity.com/paper/2011.04573/) (2020)
- [On Explainability of Graph Neural Networks via Subgraph Explorations](https://mlsanity.com/paper/2102.05152/) (2021)
- [XGNN: Towards Model-Level Explanations of Graph Neural Networks](https://mlsanity.com/paper/2006.02587/) (2020)
- [PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks](https://mlsanity.com/paper/2010.05788/) (2020)
- [GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks](https://mlsanity.com/paper/2001.06216/) (2020)
- [Explainability Techniques for Graph Convolutional Networks](https://mlsanity.com/paper/1905.13686/) (2019)
- [Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking](https://mlsanity.com/paper/2010.00577/) (2020)
- [Generative Causal Explanations for Graph Neural Networks](https://mlsanity.com/paper/2104.06643/) (2021)
- [Inducing Causal Structure for Interpretable Neural Networks](https://mlsanity.com/paper/2112.00826/) (2021)
- [Causal Attention for Interpretable and Generalizable Graph Classification](https://mlsanity.com/paper/2112.15089/) (2021)
- [CXPlain: Causal Explanations for Model Interpretation under Uncertainty](https://mlsanity.com/paper/1910.12336/) (2019)
- [The Causal-Neural Connection: Expressiveness, Learnability, and Inference](https://mlsanity.com/paper/2107.00793/) (2021)
- [Evaluating Explainability for Graph Neural Networks](https://mlsanity.com/paper/2208.09339/) (2022)
- [Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure](https://mlsanity.com/paper/2209.14107/) (2022)
- [GraphSVX: Shapley Value Explanations for Graph Neural Networks](https://mlsanity.com/paper/2104.10482/) (2021)
- [Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbation](https://mlsanity.com/paper/2008.10715/) (2020)
- [Attacking Graph-based Classification via Manipulating the Graph Structure](https://mlsanity.com/paper/1903.00553/) (2019)
- [RelEx: A Model-Agnostic Relational Model Explainer](https://mlsanity.com/paper/2006.00305/) (2020)
- [GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Games](https://mlsanity.com/paper/2201.12380/) (2022)
- [Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networks](https://mlsanity.com/paper/2105.08621/) (2021)
- [Reinforced Causal Explainer for Graph Neural Networks](https://mlsanity.com/paper/2204.11028/) (2022)
- [GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networks](https://mlsanity.com/paper/2209.07924/) (2022)
- [OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks](https://mlsanity.com/paper/2203.15209/) (2022)
- [Causal Explanations and XAI](https://mlsanity.com/paper/2201.13169/) (2022)
- [DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networks](https://mlsanity.com/paper/2303.02448/) (2023)
- [A Hard Label Black-box Adversarial Attack Against Graph Neural Networks](https://mlsanity.com/paper/2108.09513/) (2021)

## Built on by (most cited first, 9 of 9)

- [Deterministic Certification of Graph Neural Networks against Graph Poisoning Attacks with Arbitrary Perturbations](https://mlsanity.com/paper/2503.18503/) (2025)
- [Causal Graph Neural Networks for Healthcare](https://mlsanity.com/paper/2511.02531/) (2025)
- [Structure-agnostic Causal Representation Learning](https://mlsanity.com/paper/2610.00968/) (2026)
- [Leveraging Local Structure for Improving Model Explanations: An Information Propagation Approach](https://mlsanity.com/paper/2409.16429/) (2024)
- [From Observations to Causations: A GNN-based Probabilistic Prediction Framework for Causal Discovery](https://mlsanity.com/paper/2507.20349/) (2025)
- [Neurocircuitry-Inspired Hierarchical Graph Causal Attention Networks for Explainable Depression Identification](https://mlsanity.com/paper/2511.17622/) (2025)
- [CT-HEG: A Bidirectional, Timestamp-Attributed Event Graph for ICU In-Hospital Mortality Prediction - An Architectural Ablation Study](https://mlsanity.com/paper/2608.02663/) (2026)
- [Causal Memory Policy: Making Memory Utility Identifiable by Intervening on Retrieval](https://mlsanity.com/paper/2610.02070/) (2026)
- [Reasoning Models Are Accurate but Unsound on Identification](https://mlsanity.com/paper/2610.03519/) (2026)

## 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