HyperAIHyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Traffic Prediction On Pemsd4

Metrics

12 steps MAE

Results

Performance results of various models on this benchmark

Model Name
12 steps MAE
Paper TitleRepository
STD-MAE17.80Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting
PM-DMNet(R)18.37Pattern-Matching Dynamic Memory Network for Dual-Mode Traffic Prediction
PDG2Seq18.24PDG2Seq: Periodic Dynamic Graph to Sequence Model for Traffic Flow Prediction
STWave18.50When Spatio-Temporal Meet Wavelets: Disentangled Traffic Forecasting via Efficient Spectral Graph Attention Networks
FasterSTS18.49FasterSTS: A Faster Spatio-Temporal Synchronous Graph Convolutional Networks for Traffic flow Forecasting-
HTVGNN17.99A novel hybrid time-varying graph neural network for traffic flow forecasting-
STG-NCDE19.21Graph Neural Controlled Differential Equations for Traffic Forecasting
DDGCRN18.45A Decomposition Dynamic graph convolutional recurrent network for traffic forecasting
Hierarchical-Attention-LSTM (HierAttnLSTM)9.168Network Level Spatial Temporal Traffic State Forecasting with Hierarchical Attention LSTM (HierAttnLSTM)
PDFormer18.32PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction
STG-NRDE19.13Graph Neural Rough Differential Equations for Traffic Forecasting
HAGCN18.70HAGCN : Network Decentralization Attention Based Heterogeneity-Aware Spatiotemporal Graph Convolution Network for Traffic Signal Forecasting-
PM-DMNet(P)18.34Pattern-Matching Dynamic Memory Network for Dual-Mode Traffic Prediction
0 of 13 row(s) selected.
Traffic Prediction On Pemsd4 | SOTA | HyperAI