Traffic Prediction On Pems Bay
Métriques
MAE @ 12 step
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | MAE @ 12 step |
|---|---|
| spatial-temporal-attention-wavenet-a-deep | 1.89 |
| spatio-temporal-adaptive-embedding-makes | 1.91 |
| predicting-traffic-signals-on-transportation | - |
| spatio-temporal-decoupled-masked-pre-training | 1.77 |
| spatio-temporal-meta-graph-learning-for | 1.88 |
| 190600121 | 1.95 |
| rgdan-a-random-graph-diffusion-attention | 1.86 |
| spatio-temporal-graph-structure-learning-for | 2.03 |
| conditional-temporal-neural-processes-with | 1.91 |
| spatio-temporal-graph-mixformer-for-traffic | 1.857 |
| gman-a-graph-multi-attention-network-for | 1.92 |
| pre-training-enhanced-spatial-temporal-graph | 1.79 |
| decoupled-dynamic-spatial-temporal-graph | 1.85 |
| t-graphormer-using-transformers-for | 1.63 |
| diffusion-convolutional-recurrent-neural | 2.07 |
| a-time-series-is-worth-five-experts-1 | 1.69 |