benedekrozemberczki/pytorch_geometric_temporal

Health v2 · maintenance only

Adoption not part of the score

2992 stars · 403 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

PyTorch Geometric Temporal is a temporal (dynamic) extension library for PyTorch Geometric providing spatiotemporal signal processing with neural machine learning models. It includes dynamic geometric deep learning and embedding methods, dataset loaders, train-test splitters, and benchmark datasets for domains like epidemiological forecasting and traffic management.

Use cases

• forecast epidemics with spatiotemporal graph neural networks
• predict traffic on dynamic graphs
• build temporal GNN models in PyTorch
• embed nodes of evolving graphs over time
• run spatiotemporal regression on GPU
• load and split dynamic graph benchmark datasets

When to choose

• you need deep learning on dynamic or temporal graphs with PyTorch
• you want ready-made spatiotemporal GNN layers and benchmark datasets
• you need GPU-accelerated graph signal processing

When to avoid

• you work with static graphs only - plain PyTorch Geometric suffices
• you need non-PyTorch frameworks like TensorFlow or JAX
• you need lightweight classical time-series forecasting without graph structure

Facets

library · maturity active

machine-learning deep-learning graphics data-science machine-learning deep-learning graph-processing time-series data-science python cross-platform graph-neural-networks pytorch-geometric spatiotemporal temporal-graphs gnn node-embedding geometric-deep-learning gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="benedekrozemberczki/pytorch_geometric_temporal")