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

Esther Rodrigo Bonet, Tien Do Huu, Xuening Qin, Jelle Hofman, Valerio Panzica La Manna, Wilfried Philips, Nikos Deligiannis

Onderzoeksoutput: Articlepeer review

1 Citaat (Scopus)

Samenvatting

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.

Originele taal-2English
Pagina's (van-tot)499-513
Aantal pagina's15
TijdschriftIEEE Transactions on Signal and Information Processing over Networks
Volume8
DOI's
StatusPublished - 2022

Vingerafdruk

Duik in de onderzoeksthema's van 'Explaining Graph Neural Networks With Topology-Aware Node Selection: Application in Air Quality Inference'. Samen vormen ze een unieke vingerafdruk.

Citeer dit