Spatio-temporal prediction using graph neural networks: A survey

Abstract

The analysis of spatial time series is increasingly relevant as spatio-temporal data are becoming widespread due to the ever-growing diffusion of data acquisition devices. Spatio-temporal prediction is crucial for grasping insights on spatio-temporal dynamics in diverse domains. In many cases, spatio-temporal data can be effectively represented using graphs, thus making Graph Neural Networks the most sounding deep learning architecture for the modelling of spatio-temporal series. The aim of the work is to provide a self-consistent and thorough overview on Graph Neural Networks for spatio-temporal prediction, giving a taxonomy of the diverse approaches proposed in the literature. Moreover, attention is paid to the description of the most used benchmarks and metrics in different real-world spatio-temporal domains and to the discussion of the main drawbacks of spatio-temporal Graph Neural Networks. Furthermore, unlike other similar works on deep learning, statistical methods for spatio-temporal modelling are briefly surveyed in this work. Finally, insights on future developments of Graph Neural Networks for spatio-temporal prediction are suggested.