D4Explainer: In-Distribution GNN Explanations via Discrete Denoising Diffusion

Understand

The widespread deployment of Graph Neural Networks (GNNs) sparks significant interest in their explainability, which plays a vital role in model auditing and ensuring trustworthy graph learning.

• The objective of GNN explainability is to discern the underlying graph structures that have the most significant impact on model predictions.
• Ensuring that explanations generated are reliable necessitates consideration of the in-distribution property, particularly due to the vulnerability of GNNs to out-of-distribution data.
• Unfortunately, prevailing explainability methods tend to constrain the generated explanations to the structure of the original graph, thereby downplaying the significance of the in-distribution property and resulting in explanations that lack reliability.