HyperAI

Time Series Forecasting On Etth1 720 1

المقاييس

MAE
MSE

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

اسم النموذج
MAE
MSE
Paper TitleRepository
Transformer0.83991.108Long-term series forecasting with Query Selector -- efficient model of sparse attention
DiPE-Linear-0.409Disentangled Interpretable Representation for Efficient Long-term Time Series Forecasting
RLinear0.4560.442Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping
xPatch0.4590.442xPatch: Dual-Stream Time Series Forecasting with Exponential Seasonal-Trend Decomposition
SparseTSF-0.426SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameters-
DLinear0.490.472Are Transformers Effective for Time Series Forecasting?
NLinear0.4530.44Are Transformers Effective for Time Series Forecasting?
PRformer-0.489PRformer: Pyramidal Recurrent Transformer for Multivariate Time Series Forecasting
TiDE0.4650.454Long-term Forecasting with TiDE: Time-series Dense Encoder
PatchMixer0.4630.445PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting
GLinear0.53730.5923--
SCINet0.5270.544SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction
MoLE-DLinear-0.505Mixture-of-Linear-Experts for Long-term Time Series Forecasting
SegRNN0.4470.434SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting
LTBoost (drop_last=false)0.4490.435LTBoost: Boosted Hybrids of Ensemble Linear and Gradient Algorithms for the Long-term Time Series Forecasting
QuerySelector0.84281.115Long-term series forecasting with Query Selector -- efficient model of sparse attention
TSMixer0.4670.444TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting-
Informer0.7680.941Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
PatchTST/640.4680.447A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
TEFN0.4640.475Time Evidence Fusion Network: Multi-source View in Long-Term Time Series Forecasting-
0 of 22 row(s) selected.