Graph Transformer Networks (Authors' PyTorch implementation for the NeurIPS 19 paper)

This project develops a traffic prediction model combining Graph Attention Networks (GAT) and Transformer architecture to analyze spatiotemporal data from Paris traffic probes. It enhances traffic …

A physics-integrated spatiotemporal graph neural network with fundamental diagram learner for highway traffic flow prediction

Official repository for the paper "Scalable Spatiotemporal Graph Neural Networks" (AAAI 2023)