Explaining Graph Neural Networks With Topology-Aware Node Selection: Application in Air Quality Inference

Graph neural networks (GNNs) have proven their ability in modelling graph-structured data in diverse domains, including natural language processing and computer vision. However, like other deep learning models, the lack of explainability is becoming a major drawback for GNNs, especially in health-related applications such as air pollution estimation, where a model's predictions might directly affect humans' health and habits. In this paper, we present a novel post-hoc explainability framework for GNN-based models. More concretely, we propose a novel topology-aware kernelised node selection method, which we apply over the graph structural and air pollution information. Thanks to the proposed model, we are able to effectively capture the graph topology and, for a certain graph node, infer its most relevant nodes. Additionally, we propose a novel topological node embedding for each node, capturing in a vector-shape the graph walks with respect to every other graph node. To prove the effectiveness of our explanation method, we include commonly employed evaluation metrics as well as fidelity, sparsity and contrastivity, and adapt them to evaluate explainability on a regression task. Extensive experiments on two real-world air pollution data sets demonstrate and visually show the effectiveness of the proposed method.

Automated summary

This paper presents a novel post-hoc explainability framework for GNN-based models, which is especially important in health-related applications such as air pollution estimation. The proposed topology-aware kernelised node selection method and topological node embedding method effectively capture the graph topology and the relevance between nodes.