Demystifying Graph Neural Network Explanations
This work addresses the problem of unreliable explanation methods for GNNs, which is crucial for users in domains relying on graph-structured data, but it is incremental as it builds on existing perturbation-based approaches.
The paper tackles the lack of transparency in graph neural network (GNN) explanations by identifying common pitfalls in synthetic data generation, evaluation metrics, and explanation presentation, and proposes remedies based on an empirical study.
Graph neural networks (GNNs) are quickly becoming the standard approach for learning on graph structured data across several domains, but they lack transparency in their decision-making. Several perturbation-based approaches have been developed to provide insights into the decision making process of GNNs. As this is an early research area, the methods and data used to evaluate the generated explanations lack maturity. We explore these existing approaches and identify common pitfalls in three main areas: (1) synthetic data generation process, (2) evaluation metrics, and (3) the final presentation of the explanation. For this purpose, we perform an empirical study to explore these pitfalls along with their unintended consequences and propose remedies to mitigate their effects.