STGCN

Reported on 3 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Time Series3 results

Traffic PredictiononPeMS07
MAE@1h· 2017-09-14
25.38
best: 18.31 (STD-MAE)
SOTA
Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting arXiv:1709.04875
Traffic PredictiononPeMS-M
MAE (60 min)· 2017-09-14
4.02
best: 3.38 (ST-UNet)
SOTA
Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting arXiv:1709.04875
Traffic PredictiononMETR-LA
MAE @ 12 step· 2017-09-14
4.45
best: 3.08 (TITAN)
Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting arXiv:1709.04875