Graphs in Motion: Spatio-Temporal Dynamics with Graph Neural Networks

The concept behind ST-GNNs and a Pytorch Implementation for financial forecasting

Interconnected graphical data is all around us, ranging from molecular structures to social networks and design structures of cities. Graph Neural Networks (GNNs) are emerging as a powerful method of modeling and learning the spatial and graphical structure of such data. It has been applied to protein structures and other molecular applications such as drug discovery as well as modelling systems such as social networks. Recently, the standard GNN …

cities concept data design dynamics financial gnns graph graph neural networks graphs implementation modeling networks neural networks pytorch social social networks spatial temporal