A Systematic Literature Review of Spatio-Temporal Graph Neural Network Models for Time Series Forecasting and Classification

A recent systematic literature review highlights the growing significance of spatio-temporal graph neural networks (GNNs) in time series analysis. These models excel at capturing complex dependencies over time and among variables, making them invaluable for forecasting and classification tasks. This review not only summarizes various modeling approaches but also showcases the diverse application domains of GNNs, emphasizing their potential to enhance predictive accuracy in numerous fields. As industries increasingly rely on data-driven decisions, understanding these advanced models is crucial for leveraging their capabilities effectively.