D-PAD: Deep-Shallow Multi-Frequency Patterns Disentangling for Time Series Forecasting | ✓ Link | 0.374 | 0.406 | D-PAD | 2024-03-26 |
xPatch: Dual-Stream Time Series Forecasting with Exponential Seasonal-Trend Decomposition | ✓ Link | 0.391 | 0.415 | xPatch | 2024-12-23 |
PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting | ✓ Link | 0.392 | 0.414 | PatchMixer | 2023-10-01 |
Fredformer: Frequency Debiased Transformer for Time Series Forecasting | ✓ Link | 0.395 | 0.403 | Fredformer | 2024-06-13 |
UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting | ✓ Link | 0.398 | 0.407 | UniTime | 2023-10-15 |
AutoTimes: Autoregressive Time Series Forecasters via Large Language Models | ✓ Link | 0.401 | 0.429 | AutoTimes | 2024-02-04 |
SegRNN: Segment Recurrent Neural Network for Long-Term Time Series Forecasting | ✓ Link | 0.401 | 0.417 | SegRNN | 2023-08-22 |
TimeCMA: Towards LLM-Empowered Multivariate Time Series Forecasting via Cross-Modality Alignment | ✓ Link | 0.403 | 0.405 | TimeCMA | 2024-06-03 |
UniTS: A Unified Multi-Task Time Series Model | ✓ Link | 0.405 | 0.422 | UniTS-ST | 2024-02-29 |
ConvTimeNet: A Deep Hierarchical Fully Convolutional Model for Multivariate Time Series Analysis | ✓ Link | 0.405 | 0.420 | ConvTimeNet | 2024-03-03 |
ROSE: Register Assisted General Time Series Forecasting with Decomposed Frequency Learning | | 0.406 | 0.422 | ROSE | 2024-05-24 |
TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting | ✓ Link | 0.408 | 0.425 | TEMPO | 2023-10-08 |
Unified Training of Universal Time Series Forecasting Transformers | ✓ Link | 0.412 | 0.429 | MOIRAISmall | 2024-02-04 |
Adaptive Multi-Scale Decomposition Framework for Time Series Forecasting | ✓ Link | 0.418 | 0.427 | AMD | 2024-06-06 |
WinNet: Make Only One Convolutional Layer Effective for Time Series Forecasting | ✓ Link | 0.419 | 0.426 | WinNet | 2023-11-01 |
Revisiting Long-term Time Series Forecasting: An Investigation on Linear Mapping | ✓ Link | 0.42 | 0.423 | RLinear | 2023-05-18 |
TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting | ✓ Link | 0.421 | 0.436 | TSMixer | 2023-06-14 |
A Time Series is Worth 64 Words: Long-term Forecasting with Transformers | ✓ Link | 0.422 | 0.44 | PatchTST/64 | 2022-11-27 |
HiMTM: Hierarchical Multi-Scale Masked Time Series Modeling for Long-Term Forecasting | | 0.422 | 0.430 | HiMTM | 2024-01-10 |
CATS: Enhancing Multivariate Time Series Forecasting by Constructing Auxiliary Time Series as Exogenous Variables | ✓ Link | 0.423 | 0.437 | CATS | 2024-03-04 |
SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention | ✓ Link | 0.423 | 0.425 | SAMformer | 2024-02-15 |
LTBoost: Boosted Hybrids of Ensemble Linear and Gradient Algorithms for the Long-term Time Series Forecasting | ✓ Link | 0.424 | 0.423 | LTBoost (drop_last=false) | 2024-10-21 |
Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction | | 0.424 | 0.419 | GTT-Large | 2024-02-12 |
Disentangled Interpretable Representation for Efficient Long-term Time Series Forecasting | ✓ Link | 0.424 | | DiPE-Linear | 2024-11-26 |
FITS: Modeling Time Series with $10k$ Parameters | ✓ Link | 0.427 | | FITS | 2023-07-06 |
PRformer: Pyramidal Recurrent Transformer for Multivariate Time Series Forecasting | ✓ Link | 0.427 | | PRformer | 2024-08-20 |
Are Transformers Effective for Time Series Forecasting? | ✓ Link | 0.429 | 0.427 | NLinear | 2022-05-26 |
TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecasting | ✓ Link | 0.429 | 0.421 | TimeMachine | 2024-03-14 |
Generative Pretrained Hierarchical Transformer for Time Series Forecasting | ✓ Link | 0.430 | 0.423 | GPHT | 2024-02-26 |
Mixture-of-Linear-Experts for Long-term Time Series Forecasting | ✓ Link | 0.43 | | MoLE-RLinear | 2023-12-11 |
Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators | ✓ Link | 0.433 | 0.435 | PatchTST + LIFT | 2024-01-31 |
Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction | | 0.433 | 0.418 | GTT-Large(Fine-tune) | 2024-02-12 |
SparseTSF: Modeling Long-term Time Series Forecasting with 1k Parameters | ✓ Link | 0.434 | | SparseTSF | 2024-05-02 |
Long-term Forecasting with TiDE: Time-series Dense Encoder | ✓ Link | 0.435 | 0.433 | TiDE | 2023-04-17 |
Leveraging 2D Information for Long-term Time Series Forecasting with Vanilla Transformers | ✓ Link | 0.436 | 0.440 | GridTST | 2024-05-22 |
Are Transformers Effective for Time Series Forecasting? | ✓ Link | 0.439 | 0.443 | DLinear | 2022-05-26 |
FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting | ✓ Link | 0.442 | 0.445 | FiLM | 2022-05-18 |
An Analysis of Linear Time Series Forecasting Models | ✓ Link | 0.448 | | OLS | 2024-03-21 |
Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators | ✓ Link | 0.453 | 0.453 | DLinear + LIFT | 2024-01-31 |
Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting | ✓ Link | 0.454 | 0.432 | Pathformer | 2024-02-04 |
Bi-Mamba+: Bidirectional Mamba for Time Series Forecasting | | 0.455 | 0.445 | Bi-Mamba4TS | 2024-04-24 |
Unified Training of Universal Time Series Forecasting Transformers | ✓ Link | 0.456 | 0.450 | MOIRAIBase | 2024-02-04 |
Taming Pre-trained Language Models with N-gram Representations for Low-Resource Domain Adaptation | ✓ Link | 0.456 | 0.436 | LLaTA | 2021-08-01 |
CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning | ✓ Link | 0.456 | 0.436 | CALF | 2024-03-12 |
Generative Pretrained Hierarchical Transformer for Time Series Forecasting | ✓ Link | 0.456 | 0.432 | GPHT* | 2024-02-26 |
Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction | | 0.459 | 0.427 | GTT-Smal | 2024-02-12 |
Minusformer: Improving Time Series Forecasting by Progressively Learning Residuals | ✓ Link | 0.465 | 0.446 | Minusformer-96 | 2024-02-04 |
Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction | | 0.466 | 0.436 | GTT-Tiny | 2024-02-12 |
Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction | | 0.468 | 0.432 | GTT-Large(100M traing samples) | 2024-02-12 |
Mixture-of-Linear-Experts for Long-term Time Series Forecasting | ✓ Link | 0.469 | | MoLE-DLinear | 2023-12-11 |
ForecastGrapher: Redefining Multivariate Time Series Forecasting with Graph Neural Networks | | 0.472 | 0.448 | ForecastGrapher | 2024-05-28 |
BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis | ✓ Link | 0.473 | 0.451 | Basisformer | 2023-10-31 |
VCformer: Variable Correlation Transformer with Inherent Lagged Correlation for Multivariate Time Series Forecasting | ✓ Link | 0.473 | 0.449 | VCformer | 2024-05-19 |
Mamba-360: Survey of State Space Models as Transformer Alternative for Long Sequence Modelling: Methods, Applications, and Challenges | ✓ Link | 0.473 | 0.443 | Simba | 2024-04-24 |
Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction | | 0.475 | 0.444 | GTT-Large(50M traing samples) | 2024-02-12 |
Time Evidence Fusion Network: Multi-source View in Long-Term Time Series Forecasting | ✓ Link | 0.475 | 0.441 | TEFN | 2024-05-10 |
Boosting MLPs with a Coarsening Strategy for Long-Term Time Series Forecasting | ✓ Link | 0.479 | 0.450 | CPNet | 2024-05-06 |
SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion | ✓ Link | 0.480 | 0.452 | SOFTS | 2024-04-22 |
iTransformer: Inverted Transformers Are Effective for Time Series Forecasting | ✓ Link | 0.487 | 0.458 | iTransformer | 2023-10-10 |
Is Mamba Effective for Time Series Forecasting? | ✓ Link | 0.489 | 0.468 | S-Mamba | 2024-03-17 |
SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction | ✓ Link | 0.504 | 0.495 | SCINet | 2021-06-17 |
Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting | ✓ Link | 0.505 | 0.484 | Autoformer | 2021-06-24 |
ATFNet: Adaptive Time-Frequency Ensembled Network for Long-term Time Series Forecasting | ✓ Link | 0.514 | 0.521 | ATFNet | 2024-04-08 |
Unified Training of Universal Time Series Forecasting Transformers | ✓ Link | 0.514 | 0.474 | MOIRAILarge | 2024-02-04 |
RPMixer: Shaking Up Time Series Forecasting with Random Projections for Large Spatial-Temporal Data | | 0.521 | 0.498 | RPMixer | 2024-02-16 |
Attention as an RNN | ✓ Link | 0.65 | 0.55 | Aaren | 2024-05-22 |
Long-term series forecasting with Query Selector -- efficient model of sparse attention | ✓ Link | 0.8321 | 0.7041 | Transformer | 2021-07-19 |
Long-term series forecasting with Query Selector -- efficient model of sparse attention | ✓ Link | 0.8503 | 0.7039 | QuerySelector | 2021-07-19 |
Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting | ✓ Link | 0.884 | 0.753 | Informer | 2020-12-14 |
A decoder-only foundation model for time-series forecasting | ✓ Link | | 0.436 | TimesFM | 2023-10-14 |
TSMixer: An All-MLP Architecture for Time Series Forecasting | ✓ Link | | 0.431 | TSMixer | 2023-03-10 |
DeformTime: Capturing Variable Dependencies with Deformable Attention for Time Series Forecasting | ✓ Link | | 0.2158 | DeformTime | 2024-06-11 |