Parameterized Explainer for Graph Neural Network

Abstract

Despite recent progress in Graph Neural Networks (GNNs), explaining predictions made by GNNs remains a challenging open problem. The leading method independently addresses the local explanations (i.e., important subgraph structure and node features) to interpret why a GNN model makes the prediction for a single instance, e.g. a node or a graph. As a result, the explanation generated is painstakingly customized for each instance. The unique explanation interpreting each instance independently is not sufficient to provide a global understanding of the learned GNN model, leading to a lack of generalizability and hindering it from being used in the inductive setting. Besides, as it is designed for explaining a single instance, it is challenging to explain a set of instances naturally (e.g., graphs of a given class). In this study, we address these key challenges and propose PGExplainer, a parameterized explainer for GNNs. PGExplainer adopts a deep neural network to parameterize the generation process of explanations, which enables PGExplainer a natural approach to explaining multiple instances collectively. Compared to the existing work, PGExplainer has better generalization ability and can be utilized in an inductive setting easily. Experiments on both synthetic and real-life datasets show highly competitive performance with up to 24.7\% relative improvement in AUC on explaining graph classification over the leading baseline.

NeurIPS 2020

Cited by in corpus (32)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Adversarial Graph Augmentation to Improve Graph Contrastive Learning
• A Survey on Graph-Based Deep Learning for Computational Histopathology
• Self-Supervised Temporal Graph learning with Temporal and Structural Intensity Alignment
• On Explainability of Graph Neural Networks via Subgraph Explorations
• DIG: A Turnkey Library for Diving into Graph Deep Learning Research
• Toward Accurate Interpretable Predictions of Materials Properties within Transformer Language Models
• Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking
• Interpretable Graph Convolutional Network of Multi-Modality Brain Imaging for Alzheimer's Disease Diagnosis
• A Meta-Learning Approach for Training Explainable Graph Neural Networks
• Generative Causal Explanations for Graph Neural Networks
• Projective Ranking-based GNN Evasion Attacks
• View-based Explanations for Graph Neural Networks
• Towards Human-like Perception: Learning Structural Causal Model in Heterogeneous Graph
• GRETEL: A unified framework for Graph Counterfactual Explanation Evaluation
• Towards Mitigating Dimensional Collapse of Representations in Collaborative Filtering
• BrainNNExplainer: An Interpretable Graph Neural Network Framework for Brain Network based Disease Analysis
• GRAM: An Interpretable Approach for Graph Anomaly Detection using Gradient Attention Maps
• GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks
• X-CBA: Explainability Aided CatBoosted Anomal-E for Intrusion Detection System
• Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features
• Generalizing Graph Neural Networks on Out-Of-Distribution Graphs
• i-Align: an interpretable knowledge graph alignment model
• Jointly Attacking Graph Neural Network and its Explanations
• Auto-Configured Explainable Graph Neural Networks for Multi-Site Pollution Prediction
• ACGAN-GNNExplainer: Auxiliary Conditional Generative Explainer for Graph Neural Networks
• Mixture-of-Experts Graph Transformers for Interpretable Particle Collision Detection
• Towards Automated Evaluation of Explanations in Graph Neural Networks
• SEEN: Sharpening Explanations for Graph Neural Networks using Explanations from Neighborhoods
• How Faithful are Self-Explainable GNNs?
• Towards Self-Explainable Graph Neural Network
• Explainability in subgraphs-enhanced Graph Neural Networks