HTVGNN

Reported on 4 benchmarks across 1 task · 1 paper · 1 SOTA

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

Time Series4 results

Traffic PredictiononPeMS08
MAE@1h· 2024-01-17
13.24
best: 13.17 (DTRformer)
SOTA
A novel hybrid time-varying graph neural network for traffic flow forecasting arXiv:2401.10155
Traffic PredictiononPeMSD4
12 steps MAE· 2024-01-17
17.99
best: 9.168 (Hierarchical-Attention-LSTM (HierAttnLSTM))
A novel hybrid time-varying graph neural network for traffic flow forecasting arXiv:2401.10155
Traffic PredictiononPeMSD8
12 steps MAE· 2024-01-17
13.24
best: 9.215 (Hierarchical-Attention-LSTM (HierAttnLSTM))
A novel hybrid time-varying graph neural network for traffic flow forecasting arXiv:2401.10155
Traffic PredictiononPeMS04
12 Steps MAE· 2024-01-17
17.99
best: 17.8 (STD-MAE)
A novel hybrid time-varying graph neural network for traffic flow forecasting arXiv:2401.10155