Explainability in Graph Neural Networks: A Taxonomic Survey

TL;DR

This survey provides a comprehensive taxonomy of GNN explainability methods, introduces benchmark datasets, and discusses evaluation metrics, aiming to unify and advance the field of explainable graph neural networks.

Contribution

It offers the first unified taxonomy of GNN explainability methods and introduces standardized benchmark datasets for evaluation.

Findings

Unified taxonomy of GNN explainability methods

Introduction of benchmark datasets for evaluation

Analysis of current evaluation metrics

Abstract

Deep learning methods are achieving ever-increasing performance on many artificial intelligence tasks. A major limitation of deep models is that they are not amenable to interpretability. This limitation can be circumvented by developing post hoc techniques to explain the predictions, giving rise to the area of explainability. Recently, explainability of deep models on images and texts has achieved significant progress. In the area of graph data, graph neural networks (GNNs) and their explainability are experiencing rapid developments. However, there is neither a unified treatment of GNN explainability methods, nor a standard benchmark and testbed for evaluations. In this survey, we provide a unified and taxonomic view of current GNN explainability methods. Our unified and taxonomic treatments of this subject shed lights on the commonalities and differences of existing methods and set the stage for further methodological developments. To facilitate evaluations, we generate a set of benchmark graph datasets specifically for GNN explainability. We summarize current datasets and metrics for evaluating GNN explainability. Altogether, this work provides a unified methodological treatment of GNN explainability and a standardized testbed for evaluations.