Traffic Prediction On Metr La
Métriques
MAE @ 12 step
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | MAE @ 12 step |
|---|---|
| spatio-temporal-graph-structure-learning-for | 3.3 |
| t-graphormer-using-transformers-for | 3.19 |
| spatio-temporal-meta-graph-learning-for | 3.38 |
| spatio-temporal-graph-mixformer-for-traffic | 3.229 |
| a-time-series-is-worth-five-experts-1 | 3.08 |
| traffic-transformer-capturing-the-continuity | 3.28 |
| spatio-temporal-graph-convolutional-networks | 4.45 |
| pre-training-enhanced-spatial-temporal-graph | 3.37 |
| conditional-temporal-neural-processes-with | 3.50 |
| dynamic-causal-graph-convolutional-network | 3.48 |
| diffusion-convolutional-recurrent-neural | 3.6 |
| spatio-temporal-decoupled-masked-pre-training | 3.40 |
| 190600121 | 3.53 |
| st-unet-a-spatio-temporal-u-network-for-graph | 3.55 |
| structured-time-series-prediction-without | 3.42 |
| spatio-temporal-adaptive-embedding-makes | 3.34 |
| rgdan-a-random-graph-diffusion-attention | 3.40 |
| incrementally-improving-graph-wavenet | 3.47 |
| decoupled-dynamic-spatial-temporal-graph | 3.35 |
| spatial-temporal-attention-wavenet-a-deep | 3.44 |