SOTAVerified

Time Series Forecasting

Time Series Forecasting is the task of fitting a model to historical, time-stamped data in order to predict future values. Traditional approaches include moving average, exponential smoothing, and ARIMA, though models as various as RNNs, Transformers, or XGBoost can also be applied. The most popular benchmark is the ETTh1 dataset. Models are typically evaluated using the Mean Square Error (MSE) or Root Mean Square Error (RMSE).

( Image credit: ThaiBinh Nguyen )

Papers

Showing 401–450 of 1609 papers

TitleStatusHype
DiffPLF: A Conditional Diffusion Model for Probabilistic Forecasting of EV Charging LoadCode1
BACKTIME: Backdoor Attacks on Multivariate Time Series ForecastingCode1
CMoS: Rethinking Time Series Prediction Through the Lens of Chunk-wise Spatial CorrelationsCode1
A Comprehensive Survey of Deep Learning for Multivariate Time Series Forecasting: A Channel Strategy PerspectiveCode1
BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable BasisCode1
Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic ForecastingCode1
Battling the Non-stationarity in Time Series Forecasting via Test-time AdaptationCode1
FreEformer: Frequency Enhanced Transformer for Multivariate Time Series ForecastingCode1
CMamba: Channel Correlation Enhanced State Space Models for Multivariate Time Series ForecastingCode1
Discrete Graph Structure Learning for Forecasting Multiple Time SeriesCode1
Client: Cross-variable Linear Integrated Enhanced Transformer for Multivariate Long-Term Time Series ForecastingCode1
Disentangled Interpretable Representation for Efficient Long-term Time Series ForecastingCode1
Disentangling Long-Short Term State Under Unknown Interventions for Online Time Series ForecastingCode1
Spatio-Temporal Wind Speed Forecasting using Graph Networks and Novel Transformer ArchitecturesCode1
Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series ForecastingCode1
Bellman Conformal Inference: Calibrating Prediction Intervals For Time SeriesCode1
A Comprehensive Survey of Regression Based Loss Functions for Time Series ForecastingCode1
DiTEC-WDN: A Large-Scale Dataset of Hydraulic Scenarios across Multiple Water Distribution NetworksCode1
Benchmarks and Custom Package for Energy ForecastingCode1
Taming Local Effects in Graph-based Spatiotemporal ForecastingCode1
ForecastPFN: Synthetically-Trained Zero-Shot ForecastingCode1
TCCT: Tightly-Coupled Convolutional Transformer on Time Series ForecastingCode1
FrAug: Frequency Domain Augmentation for Time Series ForecastingCode1
Gateformer: Advancing Multivariate Time Series Forecasting through Temporal and Variate-Wise Attention with Gated RepresentationsCode1
FlexTSF: A Universal Forecasting Model for Time Series with Variable RegularitiesCode1
Multi-modal learning for geospatial vegetation forecastingCode1
First De-Trend then Attend: Rethinking Attention for Time-Series ForecastingCode1
Adjusting for Autocorrelated Errors in Neural Networks for Time SeriesCode1
Forecasting with Deep LearningCode1
The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series ForecastingCode1
FilterTS: Comprehensive Frequency Filtering for Multivariate Time Series ForecastingCode1
Financial time series forecasting with multi-modality graph neural networkCode1
A general framework for multi-step ahead adaptive conformal heteroscedastic time series forecastingCode1
Channel-Aware Low-Rank Adaptation in Time Series ForecastingCode1
Forecasting with Hyper-TreesCode1
FECAM: Frequency Enhanced Channel Attention Mechanism for Time Series ForecastingCode1
FDNet: Focal Decomposed Network for Efficient, Robust and Practical Time Series ForecastingCode1
Federated Learning for 5G Base Station Traffic ForecastingCode1
FCDNet: Frequency-Guided Complementary Dependency Modeling for Multivariate Time-Series ForecastingCode1
A Joint Time-frequency Domain Transformer for Multivariate Time Series ForecastingCode1
FC-GAGA: Fully Connected Gated Graph Architecture for Spatio-Temporal Traffic ForecastingCode1
Few-Shot Forecasting of Time-Series with Heterogeneous ChannelsCode1
FACTS: A Factored State-Space Framework For World ModellingCode1
Expressing Multivariate Time Series as Graphs with Time Series Attention TransformerCode1
Times2D: Multi-Period Decomposition and Derivative Mapping for General Time Series ForecastingCode1
FAITH: Frequency-domain Attention In Two Horizons for Time Series ForecastingCode1
A foundation model with multi-variate parallel attention to generate neuronal activityCode1
CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous VariablesCode1
FiLM: Frequency improved Legendre Memory Model for Long-term Time Series ForecastingCode1
ForecastNet: A Time-Variant Deep Feed-Forward Neural Network Architecture for Multi-Step-Ahead Time-Series ForecastingCode1
Show:102550
← PrevPage 9 of 33Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1InformerMSE0.88—Unverified
2QuerySelectorMSE0.85—Unverified
3TransformerMSE0.83—Unverified
4AarenMSE0.65—Unverified
5RPMixerMSE0.52—Unverified
6ATFNetMSE0.51—Unverified
7MOIRAILargeMSE0.51—Unverified
8AutoformerMSE0.51—Unverified
9SCINetMSE0.5—Unverified
10S-MambaMSE0.49—Unverified
#ModelMetricClaimedVerifiedStatus
1QuerySelectorMSE1.12—Unverified
2TransformerMSE1.11—Unverified
3InformerMSE0.94—Unverified
4GLinearMSE0.59—Unverified
5SCINetMSE0.54—Unverified
6MoLE-DLinearMSE0.51—Unverified
7PRformerMSE0.49—Unverified
8TEFNMSE0.48—Unverified
9DLinearMSE0.47—Unverified
10FiLMMSE0.47—Unverified
#ModelMetricClaimedVerifiedStatus
1TransformerMSE2.66—Unverified
2QuerySelectorMSE2.32—Unverified
3InformerMSE1.67—Unverified
4DLinearMSE0.45—Unverified
5TEFNMSE0.42—Unverified
6MoLE-DLinearMSE0.42—Unverified
7FiLMMSE0.38—Unverified
8MoLE-RLinearMSE0.37—Unverified
9SCINetMSE0.37—Unverified
10PRformerMSE0.36—Unverified
#ModelMetricClaimedVerifiedStatus
1TransformerMSE3.18—Unverified
2QuerySelectorMSE3.07—Unverified
3InformerMSE2.34—Unverified
4MoLE-DLinearMSE0.61—Unverified
5DLinearMSE0.61—Unverified
6SCINetMSE0.48—Unverified
7FiLMMSE0.44—Unverified
8TEFNMSE0.43—Unverified
9TiDEMSE0.42—Unverified
10MoLE-RLinearMSE0.41—Unverified
#ModelMetricClaimedVerifiedStatus
1MoLE-DLinearMSE0.45—Unverified
2TEFNMSE0.43—Unverified
3FiLMMSE0.41—Unverified
4PatchTST/64MSE0.41—Unverified
5TiDEMSE0.41—Unverified
6NLinearMSE0.41—Unverified
7DiPE-LinearMSE0.41—Unverified
8DLinearMSE0.41—Unverified
9RLinearMSE0.4—Unverified
10MoLE-RLinearMSE0.4—Unverified
#ModelMetricClaimedVerifiedStatus
1DLinearMSE0.38—Unverified
2TEFNMSE0.38—Unverified
3MoLE-DLinearMSE0.36—Unverified
4FiLMMSE0.36—Unverified
5NLinearMSE0.34—Unverified
6PatchTST/64MSE0.34—Unverified
7MoLE-RLinearMSE0.34—Unverified
8TiDEMSE0.33—Unverified
9PRformerMSE0.33—Unverified
10LTBoost (drop_last=false)MSE0.33—Unverified
#ModelMetricClaimedVerifiedStatus
1DLinearMSE0.29—Unverified
2TEFNMSE0.29—Unverified
3MoLE-DLinearMSE0.29—Unverified
4FiLMMSE0.28—Unverified
5NLinearMSE0.28—Unverified
6TSMixerMSE0.28—Unverified
7DiPE-LinearMSE0.28—Unverified
8PatchTST/64MSE0.27—Unverified
9MoLE-RLinearMSE0.27—Unverified
10TiDEMSE0.27—Unverified
#ModelMetricClaimedVerifiedStatus
1TEFNMSE0.38—Unverified
2MoLE-DLinearMSE0.38—Unverified
3TiDEMSE0.38—Unverified
4MoLE-RLinearMSE0.38—Unverified
5FiLMMSE0.37—Unverified
6PatchTST/64MSE0.37—Unverified
7DiPE-LinearMSE0.37—Unverified
8TSMixerMSE0.37—Unverified
9RLinearMSE0.37—Unverified
10TTMMSE0.36—Unverified
#ModelMetricClaimedVerifiedStatus
1TEFNMSE0.23—Unverified
2DLinearMSE0.22—Unverified