BetaExplainer: A Probabilistic Method to Explain Graph Neural Networks

TL;DR

BetaExplainer introduces a probabilistic approach to interpret GNNs by quantifying edge importance uncertainty and enhancing predictive accuracy on complex graph data.

Contribution

It proposes a novel sparsity-inducing prior method for GNN explanation that accounts for uncertainty and improves interpretability and performance.

Findings

Provides uncertainty quantification for edge importance

Outperforms existing explainers on challenging datasets

Enhances GNN interpretability and accuracy

Abstract

Graph neural networks (GNNs) are powerful tools for conducting inference on graph data but are often seen as "black boxes" due to difficulty in extracting meaningful subnetworks driving predictive performance. Many interpretable GNN methods exist, but they cannot quantify uncertainty in edge weights and suffer in predictive accuracy when applied to challenging graph structures. In this work, we proposed BetaExplainer which addresses these issues by using a sparsity-inducing prior to mask unimportant edges during model training. To evaluate our approach, we examine various simulated data sets with diverse real-world characteristics. Not only does this implementation provide a notion of edge importance uncertainty, it also improves upon evaluation metrics for challenging datasets compared to state-of-the art explainer methods.