VeritasYin/STGCN_IJCAI-18

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1244 stars · 327 forks observed · 2026-10-02

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

Reference implementation of Spatio-Temporal Graph Convolutional Networks (STGCN) from the IJCAI 2018 paper, a deep learning framework for traffic speed forecasting on graph-structured time series. It includes the model code and the PeMSD7 dataset for training and evaluation.

Use cases

• forecast traffic speed on road networks
• predict time series on graph-structured sensor data
• reproduce STGCN results from the IJCAI 2018 paper
• train spatio-temporal graph neural networks on PeMSD7
• build a traffic prediction model with graph convolutions
• benchmark graph convolutional models for traffic forecasting

When to choose

• you need the original STGCN implementation for traffic forecasting research
• you want a working baseline for spatio-temporal graph neural networks
• you need the PeMSD7 dataset with a ready training pipeline

When to avoid

• you need a production traffic forecasting system rather than research code
• you want actively maintained features or broad framework support
• your data is not graph-structured or road-network-like

Facets

library · maturity maintenance

deep-learning machine-learning data-science deep-learning machine-learning time-series python graph-convolutional-networks traffic-forecasting spatio-temporal time-series-prediction research-code pytorch transportation

Member repositories

For agents

markdown · JSON · MCP: product_card(name="VeritasYin/STGCN_IJCAI-18")