# VeritasYin/STGCN_IJCAI-18

[IJCAI'18] Spatio-Temporal Graph Convolutional Networks

Repository: https://github.com/VeritasYin/STGCN_IJCAI-18
Canonical: https://ross.abutalabs.com/products/stgcn_ijcai-18
Language: Python
License: BSD-2-Clause
License Family: permissive
Last push: 2026-06-14T01:20:33+00:00

## Health v2 (maintenance only)
Score: 71/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 87, release rhythm 35, longevity 100
- inputs: {"age_days": 3062, "days_push": 81, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1237, forks 327 (observed 2026-08-28T04:04:05.425851+00:00)

## What it is
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
- artifact type: library
- maturity: maintenance
- function: deep-learning, machine-learning, data-science
- domain: deep-learning, machine-learning, time-series
- platform: python
- tags: graph-convolutional-networks, traffic-forecasting, spatio-temporal, time-series-prediction, research-code, pytorch, transportation

## Member repositories
- VeritasYin/STGCN_IJCAI-18 (main) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:05.425851+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T08:21:50.786837+00:00, confidence not recorded.
  - readme: https://github.com/VeritasYin/STGCN_IJCAI-18 (fetched 2026-08-28T04:04:05.425851+00:00, sha 7faee374ae02)
- Data as of 2026-08-30T08:39:29.467469+00:00.