Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/STD-MAE

STD-MAE

Reported on 28 benchmarks across 1 task · 1 paper · 16 SOTA

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

Time Series28 results

Traffic PredictiononPeMSD7(M)
12 steps MAE· uses extra data· 2023-12-01
2.52
SOTA
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononPeMSD7(M)
12 steps RMSE· uses extra data· 2023-12-01
5.2
SOTA
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononEXPY-TKY
1 step MAE· uses extra data· 2023-12-01
5.73
SOTA
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononEXPY-TKY
3 step MAE· uses extra data· 2023-12-01
6.41
SOTA
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononEXPY-TKY
6 step MAE· uses extra data· 2023-12-01
6.75
SOTA
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononPeMS07
MAE@1h· uses extra data· 2023-12-01
18.31
SOTA
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononPeMSD7(L)
12 steps MAE· uses extra data· 2023-12-01
2.64
SOTA
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononPeMSD7(L)
12 steps RMSE· uses extra data· 2023-12-01
5.5
SOTA
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononPeMSD7
12 steps MAE· uses extra data· 2023-12-01
18.31
SOTA
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononPeMSD7
12 steps RMSE· uses extra data· 2023-12-01
31.07
SOTA
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononPEMS-BAY
MAE @ 12 step· uses extra data· 2023-12-01
1.77
best: 1.63 (T-Graphormer)
SOTA
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononPEMS-BAY
RMSE· uses extra data· 2023-12-01
4.2
best: 3.2 (T-Graphormer)
SOTA
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononMETR-LA
12 steps MAE· uses extra data· 2023-12-01
3.4
best: 3.08 (TITAN)
SOTA
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononPeMSD3
12 steps MAE· uses extra data· 2023-12-01
13.8
SOTA
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononPeMSD3
12 steps RMSE· uses extra data· 2023-12-01
24.43
SOTA
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononPeMS04
12 Steps MAE· uses extra data· 2023-12-01
17.8
SOTA
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononPeMSD7(M)
12 steps MAPE· uses extra data· 2023-12-01
6.35
best: 8.01 (STGM)
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononPeMSD4
12 steps MAE· uses extra data· 2023-12-01
17.8
best: 9.168 (Hierarchical-Attention-LSTM (HierAttnLSTM))
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononPeMSD7(L)
12 steps MAPE· uses extra data· 2023-12-01
6.65
best: 7.31 (STG-NCDE)
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononPeMSD8
12 steps MAE· uses extra data· 2023-12-01
13.44
best: 9.215 (Hierarchical-Attention-LSTM (HierAttnLSTM))
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononPeMSD8
12 steps MAPE· uses extra data· 2023-12-01
8.76
best: 9.92 (STG-NCDE)
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononPeMSD8
12 steps RMSE· uses extra data· 2023-12-01
22.47
best: 22.32 (Hierarchical-Attention-LSTM (HierAttnLSTM))
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononPeMSD7
12 steps MAPE· uses extra data· 2023-12-01
7.72
best: 8.8 (STG-NCDE)
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononMETR-LA
12 steps MAPE· uses extra data· 2023-12-01
9.59
best: 9.94 (DCGCN)
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononMETR-LA
12 steps RMSE· uses extra data· 2023-12-01
7.07
best: 6.12 (T-Graphormer)
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononMETR-LA
MAE @ 12 step· uses extra data· 2023-12-01
3.4
best: 3.08 (TITAN)
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononMETR-LA
MAE @ 3 step· uses extra data· 2023-12-01
2.62
best: 2.41 (TITAN)
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516
Traffic PredictiononPeMSD3
12 steps MAPE· uses extra data· 2023-12-01
13.96
best: 15.06 (STG-NCDE)
Spatial-Temporal-Decoupled Masked Pre-training for Spatiotemporal Forecasting arXiv:2312.00516