Abstract: Attributed graphs have an additional sign vector for each node. Typically, edge signs represent like or dislike relationship between the node pairs. This has applications in domains, such as ...

STM-Graph is a Python framework for analyzing spatial-temporal urban data and doing predictions using Graph Neural Networks. It provides a complete end-to-end pipeline from raw event data to trained ...

This project uses spatio-temporal graph neural networks to perform weather forecasting on ERA5 reanalysis data. The model treats the global weather system as a graph where each grid point is a node ...

Abstract: Graph Neural Networks (GNNs) exploit topological structures—namely, node-to-node connections—to aggregate contextual information, thereby achieving strong performance across diverse domains.