GNNExplainer: Generating Explanations for Graph Neural Networks

TL;DR

GNNExplainer is a novel, model-agnostic method that provides interpretable explanations for GNN predictions by identifying key subgraphs and features, improving understanding and debugging of GNN models.

Contribution

It introduces the first general approach for explaining any GNN's predictions by optimizing mutual information between predictions and subgraph structures.

Findings

Outperforms baselines by 17.1% on synthetic and real-world graphs.

Effectively identifies important graph structures and node features.

Enables visualization and interpretation of GNN decisions.

Abstract

Graph Neural Networks (GNNs) are a powerful tool for machine learning on graphs.GNNs combine node feature information with the graph structure by recursively passing neural messages along edges of the input graph. However, incorporating both graph structure and feature information leads to complex models, and explaining predictions made by GNNs remains unsolved. Here we propose GNNExplainer, the first general, model-agnostic approach for providing interpretable explanations for predictions of any GNN-based model on any graph-based machine learning task. Given an instance, GNNExplainer identifies a compact subgraph structure and a small subset of node features that have a crucial role in GNN's prediction. Further, GNNExplainer can generate consistent and concise explanations for an entire class of instances. We formulate GNNExplainer as an optimization task that maximizes the mutual information between a GNN's prediction and distribution of possible subgraph structures. Experiments on synthetic and real-world graphs show that our approach can identify important graph structures as well as node features, and outperforms baselines by 17.1% on average. GNNExplainer provides a variety of benefits, from the ability to visualize semantically relevant structures to interpretability, to giving insights into errors of faulty GNNs.