Go to NeurIPS 2025 Workshop NPGML homepageMetropolis-Scale Road Network Datasets for Fine-Grained Urban Traffic Forecasting
Keywords: traffic forecasting, spatiotemporal forecasting, graph neural network, dataset, benchmark
Abstract: Traffic forecasting on road networks is a complex task of significant practical importance and spatiotemporal graph neural networks (GNNs) have become the most popular approach for this task. The proper evaluation of traffic forecasting methods requires realistic datasets, but current publicly available benchmarks have significant drawbacks, including the absence of information about road connectivity for road graph construction, limited information about road properties, and relatively small size. Further, current datasets mostly contain information about intercity highways with sparsely located sensors, while city road networks arguably present a more challenging forecasting task due to much denser roads and more complex urban traffic patterns. In this work, we provide a more complete, realistic, and challenging benchmark for traffic forecasting by releasing datasets representing the road networks of two major cities, with the largest containing almost 100,000 road segments (more than a 10-fold increase relative to existing datasets). Our datasets contain rich road features and provide fine-grained data about both traffic volume and traffic speed, enabling building of more holistic traffic forecasting systems. We show that most current implementations of neural spatiotemporal models for traffic forecasting have problems scaling to datasets of our size. To overcome this issue, we propose an alternative approach to neural traffic forecasting that uses a GNN without a dedicated module for temporal sequence processing, thus achieving much better scalability, while also demonstrating stronger forecasting performance. We hope our datasets and modeling insights will serve as valuable resources for research in traffic forecasting.
Submission Number: 75
Loading