Explaining the Explainers in Graph Neural Networks: a Comparative Study

Abstract

Following a fast initial breakthrough in graph based learning, Graph Neural Networks (GNNs) have reached a widespread application in many science and engineering fields, prompting the need for methods to understand their decision process. GNN explainers have started to emerge in recent years, with a multitude of methods both novel or adapted from other domains. To sort out this plethora of alternative approaches, several studies have benchmarked the performance of different explainers in terms of various explainability metrics. However, these earlier works make no attempts at providing insights into why different GNN architectures are more or less explainable, or which explainer should be preferred in a given setting. In this survey, we fill these gaps by devising a systematic experimental study, which tests ten explainers on eight representative architectures trained on six carefully designed graph and node classification datasets. With our results we provide key insights on the choice and applicability of GNN explainers, we isolate key components that make them usable and successful and provide recommendations on how to avoid common interpretation pitfalls. We conclude by highlighting open questions and directions of possible future research.

References in corpus (17)

• Emergence of scaling in random networks
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Inductive Representation Learning on Large Graphs
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• XGNN: Towards Model-Level Explanations of Graph Neural Networks
• Higher-Order Explanations of Graph Neural Networks via Relevant Walks
• Reinforced Causal Explainer for Graph Neural Networks
• PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks
• Higher-order Clustering and Pooling for Graph Neural Networks
• Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunities
• A Meta-Learning Approach for Training Explainable Graph Neural Networks
• Higher-Order Attribute-Enhancing Heterogeneous Graph Neural Networks
• Rethinking Graph Neural Networks for the Graph Coloring Problem
• Learning Equivariant Energy Based Models with Equivariant Stein Variational Gradient Descent
• Globally Interpretable Graph Learning via Distribution Matching
• Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networks

Cited by in corpus (2)

• Explaining GNN Explanations with Edge Gradients
• A method for the systematic generation of graph XAI benchmarks via Weisfeiler-Leman coloring