Startseite Neuigkeiten Neueste Forschungsarbeiten Tutorials Datensätze Wiki SOTA LLM-Modelle GPU-Rangliste Veranstaltungen

Deutsch

Traffic Prediction On Pems Bay

Metriken

MAE @ 12 step

Ergebnisse

Leistungsergebnisse verschiedener Modelle zu diesem Benchmark

Modellname	MAE @ 12 step	Paper Title	Repository
STAWnet	1.89	Spatial‐temporal attention wavenet: A deep learning framework for traffic prediction considering spatial‐temporal dependencies
STAEformer	1.91	STAEformer: Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting
STBayesian	-	Traffic signal prediction on transportation networks using spatio-temporal correlations on graphs
STD-MAE	1.77	Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting
MegaCRN	1.88	Spatio-Temporal Meta-Graph Learning for Traffic Forecasting
Graph Wave-Net	1.95	Graph WaveNet for Deep Spatial-Temporal Graph Modeling
RGDAN	1.86	RGDAN: A random graph diffusion attention network for traffic prediction
SLCNN	2.03	Spatio-Temporal Graph Structure Learning for Traffic Forecasting	-
GWNET-Cov	1.91	Conditional Temporal Neural Processes with Covariance Loss	-
STGM	1.857	Spatio-Temporal Graph Mixformer for Traffic Forecasting
GMAN	1.92	GMAN: A Graph Multi-Attention Network for Traffic Prediction
STEP	1.79	Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting
D2STGNN	1.85	Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting
T-Graphormer	1.63	T-Graphormer: Using Transformers for Spatiotemporal Forecasting
DCRNN	2.07	Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
TITAN	1.69	A Time Series is Worth Five Experts: Heterogeneous Mixture of Experts for Traffic Flow Prediction

0 of 16 row(s) selected.