PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks
This addresses the problem of interpretability in GNNs for researchers and practitioners, offering a novel explanation approach with theoretical guarantees, though it is incremental in improving over prior methods.
The paper tackles the challenge of explaining Graph Neural Networks (GNNs) predictions by proposing PGM-Explainer, a model-agnostic method that identifies crucial graph components and generates explanations as probabilistic graphical models, achieving better performance than existing explainers in benchmark tasks.
In Graph Neural Networks (GNNs), the graph structure is incorporated into the learning of node representations. This complex structure makes explaining GNNs' predictions become much more challenging. In this paper, we propose PGM-Explainer, a Probabilistic Graphical Model (PGM) model-agnostic explainer for GNNs. Given a prediction to be explained, PGM-Explainer identifies crucial graph components and generates an explanation in form of a PGM approximating that prediction. Different from existing explainers for GNNs where the explanations are drawn from a set of linear functions of explained features, PGM-Explainer is able to demonstrate the dependencies of explained features in form of conditional probabilities. Our theoretical analysis shows that the PGM generated by PGM-Explainer includes the Markov-blanket of the target prediction, i.e. including all its statistical information. We also show that the explanation returned by PGM-Explainer contains the same set of independence statements in the perfect map. Our experiments on both synthetic and real-world datasets show that PGM-Explainer achieves better performance than existing explainers in many benchmark tasks.