XGNN: Towards Model-Level Explanations of Graph Neural Networks

Abstract

Graphs neural networks (GNNs) learn node features by aggregating and combining neighbor information, which have achieved promising performance on many graph tasks. However, GNNs are mostly treated as black-boxes and lack human intelligible explanations. Thus, they cannot be fully trusted and used in certain application domains if GNN models cannot be explained. In this work, we propose a novel approach, known as XGNN, to interpret GNNs at the model-level. Our approach can provide high-level insights and generic understanding of how GNNs work. In particular, we propose to explain GNNs by training a graph generator so that the generated graph patterns maximize a certain prediction of the model.We formulate the graph generation as a reinforcement learning task, where for each step, the graph generator predicts how to add an edge into the current graph. The graph generator is trained via a policy gradient method based on information from the trained GNNs. In addition, we incorporate several graph rules to encourage the generated graphs to be valid. Experimental results on both synthetic and real-world datasets show that our proposed methods help understand and verify the trained GNNs. Furthermore, our experimental results indicate that the generated graphs can provide guidance on how to improve the trained GNNs.

References in corpus (1)

• Interpretable Explanations of Black Boxes by Meaningful Perturbation

Cited by in corpus (21)

• From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI
• Higher-Order Explanations of Graph Neural Networks via Relevant Walks
• Trustworthy Graph Neural Networks: Aspects, Methods and Trends
• Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning
• A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
• Reinforced Causal Explainer for Graph Neural Networks
• Explaining the Explainers in Graph Neural Networks: a Comparative Study
• Deeper Insights into Deep Graph Convolutional Networks: Stability and Generalization
• A Meta-Learning Approach for Training Explainable Graph Neural Networks
• GNNShap: Scalable and Accurate GNN Explanation using Shapley Values
• View-based Explanations for Graph Neural Networks
• Counterfactual Learning on Graphs: A Survey
• Beyond Fidelity: Explaining Vulnerability Localization of Learning-based Detectors
• Discovering robust biomarkers of psychiatric disorders from resting-state functional MRI via graph neural networks: A systematic review
• EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learning
• Generating Post-hoc Explanations for Skip-gram-based Node Embeddings by Identifying Important Nodes with Bridgeness
• Globally Interpretable Graph Learning via Distribution Matching
• ACGAN-GNNExplainer: Auxiliary Conditional Generative Explainer for Graph Neural Networks
• XInsight: Revealing Model Insights for GNNs with Flow-based Explanations
• The GECo algorithm for Graph Neural Networks Explanation
• MBExplainer: Multilevel bandit-based explanations for downstream models with augmented graph embeddings