diff --git a/README.md b/README.md index 9af59966..bd8b0623 100644 --- a/README.md +++ b/README.md @@ -6,7 +6,7 @@
-[**English**](./README.md) **|** +[**English**](./README.md) **|** [**简体中文**](./README_CN.md)
@@ -25,15 +25,15 @@
-🎉 [**Getting Started**](./tutorial/getting_started.md) **|** +🎉 [**Getting Started**](./tutorial/getting_started.md) **|** 💡 [**Overall Design**](./tutorial/overall_design.md) -📦 [**Dataset**](./tutorial/dataset_design.md) **|** -🛠️ [**Scaler**](./tutorial/scaler_design.md) **|** -🧠 [**Model**](./tutorial/model_design.md) **|** -📉 [**Metrics**](./tutorial/metrics_design.md) **|** -🏃‍♂️ [**Runner**](./tutorial/runner_design.md) **|** -📜 [**Config**](./tutorial/config_design.md.md) **|** +📦 [**Dataset**](./tutorial/dataset_design.md) **|** +🛠️ [**Scaler**](./tutorial/scaler_design.md) **|** +🧠 [**Model**](./tutorial/model_design.md) **|** +📉 [**Metrics**](./tutorial/metrics_design.md) **|** +🏃‍♂️ [**Runner**](./tutorial/runner_design.md) **|** +📜 [**Config**](./tutorial/config_design.md.md) **|** 📜 [**Baselines**](./baselines/)
@@ -48,9 +48,9 @@ On the other hand, BasicTS offers a **user-friendly and easily extensible** inte You can find detailed tutorials in [Getting Started](./tutorial/getting_started.md). Additionally, we are collecting **ToDo** and **HowTo** items. If you need more features (e.g., additional datasets or benchmark models) or tutorials, feel free to open an issue or leave a comment [here](https://github.com/zezhishao/BasicTS/issues/95). - -> [!IMPORTANT] +> [!IMPORTANT] > If you find this repository helpful for your work, please consider citing the following benchmarking paper: +> > ```LaTeX > @article{shao2023exploring, > title={Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis}, @@ -58,10 +58,10 @@ You can find detailed tutorials in [Getting Started](./tutorial/getting_started. > journal={arXiv preprint arXiv:2310.06119}, > year={2023} > } -> ``` +> ``` +> > 🔥🔥🔥 ***The paper has been accepted by IEEE TKDE! You can check it out [here](https://arxiv.org/abs/2310.06119).*** 🔥🔥🔥 - ## ✨ Highlighted Features ### Fair Performance Review @@ -105,83 +105,81 @@ The code links (💻Code) in the table below point to the official implementatio

Spatial-Temporal Forecasting

 +| 📊Baseline | 📝Title | 📄Paper | 💻Code | 🏛Venue | 🎯Task | +| :--------- | :------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------- | :----- | +| BigST | Linear Complexity Spatio-Temporal Graph Neural Network for Traffic Forecasting on Large-Scale Road Networks | [Link](https://dl.acm.org/doi/10.14778/3641204.3641217) | [Link](https://github.com/usail-hkust/BigST?tab=readme-ov-file) | VLDB'24 | STF | +| STDMAE | Spatio-Temporal-Decoupled Masked Pre-training for Traffic Forecasting | [Link](https://arxiv.org/abs/2312.00516) | [Link](https://github.com/Jimmy-7664/STD-MAE) | IJCAI'24 | STF | +| STWave | When Spatio-Temporal Meet Wavelets: Disentangled Traffic Forecasting via Efficient Spectral Graph Attention Networks | [Link](https://ieeexplore.ieee.org/document/10184591) | [Link](https://github.com/LMissher/STWave) | ICDE'23 | STF | +| STAEformer | Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting | [Link](https://arxiv.org/abs/2308.10425) | [Link](https://github.com/XDZhelheim/STAEformer) | CIKM'23 | STF | +| MegaCRN | Spatio-Temporal Meta-Graph Learning for Traffic Forecasting | [Link](https://aps.arxiv.org/abs/2212.05989) | [Link](https://github.com/deepkashiwa20/MegaCRN) | AAAI'23 | STF | +| DGCRN | Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution | [Link](https://arxiv.org/abs/2104.14917) | [Link](https://github.com/tsinghua-fib-lab/Traffic-Benchmark) | ACM TKDD'23 | STF | +| STID | Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting | [Link](https://arxiv.org/abs/2208.05233) | [Link](https://github.com/zezhishao/STID) | CIKM'22 | STF | +| STEP | Pretraining Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting | [Link](https://arxiv.org/abs/2206.09113) | [Link](https://github.com/GestaltCogTeam/STEP?tab=readme-ov-file) | SIGKDD'22 | STF | +| D2STGNN | Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting | [Link](https://arxiv.org/abs/2206.09112) | [Link](https://github.com/zezhishao/D2STGNN) | VLDB'22 | STF | +| STNorm | Spatial and Temporal Normalization for Multi-variate Time Series Forecasting | [Link](https://dl.acm.org/doi/10.1145/3447548.3467330) | [Link](https://github.com/JLDeng/ST-Norm/blob/master/models/Wavenet.py) | SIGKDD'21 | STF | +| STGODE | Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting | [Link](https://arxiv.org/abs/2106.12931) | [Link](https://github.com/square-coder/STGODE) | SIGKDD'21 | STF | +| GTS | Discrete Graph Structure Learning for Forecasting Multiple Time Series | [Link](https://arxiv.org/abs/2101.06861) | [Link](https://github.com/chaoshangcs/GTS) | ICLR'21 | STF | +| StemGNN | Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting | [Link](https://arxiv.org/abs/2103.07719) | [Link](https://github.com/microsoft/StemGNN) | NeurIPS'20 | STF | +| MTGNN | Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks | [Link](https://arxiv.org/abs/2005.11650) | [Link](https://github.com/nnzhan/MTGNN) | SIGKDD'20 | STF | +| AGCRN | Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting | [Link](https://arxiv.org/abs/2007.02842) | [Link](https://github.com/LeiBAI/AGCRN) | NeurIPS'20 | STF | +| GWNet | Graph WaveNet for Deep Spatial-Temporal Graph Modeling | [Link](https://arxiv.org/abs/1906.00121) | [Link](https://github.com/nnzhan/Graph-WaveNet/blob/master/model.py) | IJCAI'19 | STF | +| STGCN | Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting | [Link](https://arxiv.org/abs/1709.04875) | [Link](https://github.com/VeritasYin/STGCN_IJCAI-18) | IJCAI'18 | STF | +| DCRNN | Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting | [Link](https://arxiv.org/abs/1707.01926) | [Link1](https://github.com/chnsh/DCRNN_PyTorch/blob/pytorch_scratch/model/pytorch/dcrnn_cell.py), [Link2](https://github.com/chnsh/DCRNN_PyTorch/blob/pytorch_scratch/model/pytorch/dcrnn_model.py) | ICLR'18 | STF | -| 📊Baseline | 📝Title | 📄Paper | 💻Code | 🏛Venue | 🎯Task | -|:-------------|:---------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------|:---------| -| BigST | Linear Complexity Spatio-Temporal Graph Neural Network for Traffic Forecasting on Large-Scale Road Networks | [Link](https://dl.acm.org/doi/10.14778/3641204.3641217) | [Link](https://github.com/usail-hkust/BigST?tab=readme-ov-file) | VLDB'24 | STF | -| STDMAE | Spatio-Temporal-Decoupled Masked Pre-training for Traffic Forecasting | [Link](https://arxiv.org/abs/2312.00516) | [Link](https://github.com/Jimmy-7664/STD-MAE) | IJCAI'24 | STF | -| STWave | When Spatio-Temporal Meet Wavelets: Disentangled Traffic Forecasting via Efficient Spectral Graph Attention Networks | [Link](https://ieeexplore.ieee.org/document/10184591) | [Link](https://github.com/LMissher/STWave) | ICDE'23 | STF | -| STAEformer | Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting | [Link](https://arxiv.org/abs/2308.10425) | [Link](https://github.com/XDZhelheim/STAEformer) | CIKM'23 | STF | -| MegaCRN | Spatio-Temporal Meta-Graph Learning for Traffic Forecasting | [Link](https://aps.arxiv.org/abs/2212.05989) | [Link](https://github.com/deepkashiwa20/MegaCRN) | AAAI'23 | STF | -| DGCRN | Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution | [Link](https://arxiv.org/abs/2104.14917) | [Link](https://github.com/tsinghua-fib-lab/Traffic-Benchmark) | ACM TKDD'23 | STF | -| STID | Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting | [Link](https://arxiv.org/abs/2208.05233) | [Link](https://github.com/zezhishao/STID) | CIKM'22 | STF | -| STEP | Pretraining Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting | [Link](https://arxiv.org/abs/2206.09113) | [Link](https://github.com/GestaltCogTeam/STEP?tab=readme-ov-file) | SIGKDD'22 | STF | -| D2STGNN | Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting | [Link](https://arxiv.org/abs/2206.09112) | [Link](https://github.com/zezhishao/D2STGNN) | VLDB'22 | STF | -| STNorm | Spatial and Temporal Normalization for Multi-variate Time Series Forecasting | [Link](https://dl.acm.org/doi/10.1145/3447548.3467330) | [Link](https://github.com/JLDeng/ST-Norm/blob/master/models/Wavenet.py) | SIGKDD'21 | STF | -| STGODE | Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting | [Link](https://arxiv.org/abs/2106.12931) | [Link](https://github.com/square-coder/STGODE) | SIGKDD'21 | STF | -| GTS | Discrete Graph Structure Learning for Forecasting Multiple Time Series | [Link](https://arxiv.org/abs/2101.06861) | [Link](https://github.com/chaoshangcs/GTS) | ICLR'21 | STF | -| StemGNN | Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting | [Link](https://arxiv.org/abs/2103.07719) | [Link](https://github.com/microsoft/StemGNN) | NeurIPS'20 | STF | -| MTGNN | Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks | [Link](https://arxiv.org/abs/2005.11650) | [Link](https://github.com/nnzhan/MTGNN) | SIGKDD'20 | STF | -| AGCRN | Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting | [Link](https://arxiv.org/abs/2007.02842) | [Link](https://github.com/LeiBAI/AGCRN) | NeurIPS'20 | STF | -| GWNet | Graph WaveNet for Deep Spatial-Temporal Graph Modeling | [Link](https://arxiv.org/abs/1906.00121) | [Link](https://github.com/nnzhan/Graph-WaveNet/blob/master/model.py) | IJCAI'19 | STF | -| STGCN | Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting | [Link](https://arxiv.org/abs/1709.04875) | [Link](https://github.com/VeritasYin/STGCN_IJCAI-18) | IJCAI'18 | STF | -| DCRNN | Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting | [Link](https://arxiv.org/abs/1707.01926) | [Link1](https://github.com/chnsh/DCRNN_PyTorch/blob/pytorch_scratch/model/pytorch/dcrnn_cell.py), [Link2](https://github.com/chnsh/DCRNN_PyTorch/blob/pytorch_scratch/model/pytorch/dcrnn_model.py) | ICLR'18 | STF |

Long-Term Time Series Forecasting

 +| 📊Baseline | 📝Title | 📄Paper | 💻Code | 🏛Venue | 🎯Task | +| :------------ | :------------------------------------------------------------------------------------------------------- | :----------------------------------------------------- | :---------------------------------------------------------------------------- | :--------- | :----- | +| CATS | Are Self-Attentions Effective for Time Series Forecasting? | [Link](https://arxiv.org/pdf/2405.16877) | [Link](https://github.com/dongbeank/CATS) | NeurIPS'24 | LTSF | +| Sumba | Structured Matrix Basis for Multivariate Time Series Forecasting with Interpretable Dynamics | [Link](https://xiucheng.org/assets/pdfs/nips24-sumba.pdf) | [Link](https://github.com/chenxiaodanhit/Sumba/) | NeurIPS'24 | LTSF | +| GLAFF | Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective | [Link](https://arxiv.org/pdf/2409.18696) | [Link](https://github.com/ForestsKing/GLAFF) | NeurIPS'24 | LTSF | +| CycleNet | CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns Forecasting | [Link](https://arxiv.org/pdf/2409.18479) | [Link](https://github.com/ACAT-SCUT/CycleNet) | NeurIPS'24 | LTSF | +| Fredformer | Fredformer: Frequency Debiased Transformer for Time Series Forecasting | [Link](https://arxiv.org/pdf/2406.09009) | [Link](https://github.com/chenzRG/Fredformer) | KDD'24 | LTSF | +| UMixer | An Unet-Mixer Architecture with Stationarity Correction for Time Series Forecasting | [Link](https://arxiv.org/abs/2401.02236) | [Link](https://github.com/XiangMa-Shaun/U-Mixer) | AAAI'24 | LTSF | +| TimeMixer | Decomposable Multiscale Mixing for Time Series Forecasting | [Link](https://arxiv.org/html/2405.14616v1) | [Link](https://github.com/kwuking/TimeMixer) | ICLR'24 | LTSF | +| Time-LLM | Time-LLM: Time Series Forecasting by Reprogramming Large Language Models | [Link](https://arxiv.org/abs/2310.01728) | [Link](https://github.com/KimMeen/Time-LLM) | ICLR'24 | LTSF | +| SparseTSF | Modeling LTSF with 1k Parameters | [Link](https://arxiv.org/abs/2405.00946) | [Link](https://github.com/lss-1138/SparseTSF) | ICML'24 | LTSF | +| iTrainsformer | Inverted Transformers Are Effective for Time Series Forecasting | [Link](https://arxiv.org/abs/2310.06625) | [Link](https://github.com/thuml/iTransformer) | ICLR'24 | LTSF | +| Koopa | Learning Non-stationary Time Series Dynamics with Koopman Predictors | [Link](https://arxiv.org/abs/2305.18803) | [Link](https://github.com/thuml/Koopa) | NeurIPS'24 | LTSF | +| CrossGNN | CrossGNN: Confronting Noisy Multivariate Time Series Via Cross Interaction Refinement | [Link](https://openreview.net/pdf?id=xOzlW2vUYc) | [Link](https://github.com/hqh0728/CrossGNN) | NeurIPS'23 | LTSF | +| NLinear | Are Transformers Effective for Time Series Forecasting? | [Link](https://arxiv.org/abs/2205.13504) | [Link](https://github.com/cure-lab/DLinear) | AAAI'23 | LTSF | +| Crossformer | Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting | [Link](https://openreview.net/forum?id=vSVLM2j9eie) | [Link](https://github.com/Thinklab-SJTU/Crossformer) | ICLR'23 | LTSF | +| DLinear | Are Transformers Effective for Time Series Forecasting? | [Link](https://arxiv.org/abs/2205.13504) | [Link](https://github.com/cure-lab/DLinear) | AAAI'23 | LTSF | +| DSformer | A Double Sampling Transformer for Multivariate Time Series Long-term Prediction | [Link](https://arxiv.org/abs/2308.03274) | [Link](https://github.com/ChengqingYu/DSformer) | CIKM'23 | LTSF | +| SegRNN | Segment Recurrent Neural Network for Long-Term Time Series Forecasting | [Link](https://arxiv.org/abs/2308.11200) | [Link](https://github.com/lss-1138/SegRNN) | arXiv | LTSF | +| MTS-Mixers | Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing | [Link](https://arxiv.org/abs/2302.04501) | [Link](https://github.com/plumprc/MTS-Mixers) | arXiv | LTSF | +| LightTS | Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP | [Link](https://arxiv.org/abs/2207.01186) | [Link](https://github.com/thuml/Time-Series-Library/blob/main/models/LightTS.py) | arXiv | LTSF | +| ETSformer | Exponential Smoothing Transformers for Time-series Forecasting | [Link](https://arxiv.org/abs/2202.01381) | [Link](https://github.com/salesforce/ETSformer) | arXiv | LTSF | +| NHiTS | Neural Hierarchical Interpolation for Time Series Forecasting | [Link](https://arxiv.org/abs/2201.12886) | [Link](https://github.com/cchallu/n-hits) | AAAI'23 | LTSF | +| PatchTST | A Time Series is Worth 64 Words: Long-term Forecasting with Transformers | [Link](https://arxiv.org/abs/2211.14730) | [Link](https://github.com/yuqinie98/PatchTST) | ICLR'23 | LTSF | +| TiDE | Long-term Forecasting with TiDE: Time-series Dense Encoder | [Link](https://arxiv.org/abs/2304.08424) | [Link](https://github.com/lich99/TiDE) | TMLR'23 | LTSF | +| TimesNet | Temporal 2D-Variation Modeling for General Time Series Analysis | [Link](https://openreview.net/pdf?id=ju_Uqw384Oq) | [Link](https://github.com/thuml/TimesNet) | ICLR'23 | LTSF | +| Triformer | Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting | [Link](https://arxiv.org/abs/2204.13767) | [Link](https://github.com/razvanc92/triformer) | IJCAI'22 | LTSF | +| NSformer | Exploring the Stationarity in Time Series Forecasting | [Link](https://arxiv.org/abs/2205.14415) | [Link](https://github.com/thuml/Nonstationary_Transformers) | NeurIPS'22 | LTSF | +| FiLM | Frequency improved Legendre Memory Model for LTSF | [Link](https://arxiv.org/abs/2205.08897) | [Link](https://github.com/tianzhou2011/FiLM) | NeurIPS'22 | LTSF | +| FEDformer | Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting | [Link](https://arxiv.org/abs/2201.12740v3) | [Link](https://github.com/MAZiqing/FEDformer) | ICML'22 | LTSF | +| Pyraformer | Low complexity pyramidal Attention For Long-range Time Series Modeling and Forecasting | [Link](https://openreview.net/forum?id=0EXmFzUn5I) | [Link](https://github.com/ant-research/Pyraformer) | ICLR'22 | LTSF | +| HI | Historical Inertia: A Powerful Baseline for Long Sequence Time-series Forecasting | [Link](https://arxiv.org/abs/2103.16349) | None | CIKM'21 | LTSF | +| Autoformer | Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting | [Link](https://arxiv.org/abs/2106.13008) | [Link](https://github.com/thuml/Autoformer) | NeurIPS'21 | LTSF | +| Informer | Beyond Efficient Transformer for Long Sequence Time-Series Forecasting | [Link](https://arxiv.org/abs/2012.07436) | [Link](https://github.com/zhouhaoyi/Informer2020) | AAAI'21 | LTSF | -| 📊Baseline | 📝Title | 📄Paper | 💻Code | 🏛Venue | 🎯Task | -|:--------------|:------------------------------------------------------------------------------------------------|:----------------------------------------------------|:---------------------------------------------------------------------------------|:-----------|:---------| -| CATS | Are Self-Attentions Effective for Time Series Forecasting? | [Link]( https://arxiv.org/pdf/2405.16877) | [Link](https://github.com/dongbeank/CATS) | NeurIPS'24 | LTSF | -| Sumba | Structured Matrix Basis for Multivariate Time Series Forecasting with Interpretable Dynamics | [Link]( https://xiucheng.org/assets/pdfs/nips24-sumba.pdf) | [Link](https://github.com/chenxiaodanhit/Sumba/) | NeurIPS'24 | LTSF | -| GLAFF | Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective | [Link]( https://arxiv.org/pdf/2409.18696) | [Link](https://github.com/ForestsKing/GLAFF) | NeurIPS'24 | LTSF | -| CycleNet | CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns Forecasting | [Link]( https://arxiv.org/pdf/2409.18479) | [Link](https://github.com/ACAT-SCUT/CycleNet) | NeurIPS'24 | LTSF | -| Fredformer | Fredformer: Frequency Debiased Transformer for Time Series Forecasting | [Link]( https://arxiv.org/pdf/2406.09009) | [Link](https://github.com/chenzRG/Fredformer) | KDD'24 | LTSF | -| UMixer | An Unet-Mixer Architecture with Stationarity Correction for Time Series Forecasting | [Link](https://arxiv.org/abs/2401.02236) | [Link](https://github.com/XiangMa-Shaun/U-Mixer) | AAAI'24 | LTSF | -| TimeMixer | Decomposable Multiscale Mixing for Time Series Forecasting | [Link](https://arxiv.org/html/2405.14616v1) | [Link](https://github.com/kwuking/TimeMixer) | ICLR'24 | LTSF | -| Time-LLM | Time-LLM: Time Series Forecasting by Reprogramming Large Language Models | [Link](https://arxiv.org/abs/2310.01728) | [Link](https://github.com/KimMeen/Time-LLM) | ICLR'24 | LTSF | -| SparseTSF | Modeling LTSF with 1k Parameters | [Link](https://arxiv.org/abs/2405.00946) | [Link](https://github.com/lss-1138/SparseTSF) | ICML'24 | LTSF | -| iTrainsformer | Inverted Transformers Are Effective for Time Series Forecasting | [Link](https://arxiv.org/abs/2310.06625) | [Link](https://github.com/thuml/iTransformer) | ICLR'24 | LTSF | -| Koopa | Learning Non-stationary Time Series Dynamics with Koopman Predictors | [Link](https://arxiv.org/abs/2305.18803) | [Link](https://github.com/thuml/Koopa) | NeurIPS'24 | LTSF | -| CrossGNN | CrossGNN: Confronting Noisy Multivariate Time Series Via Cross Interaction Refinement | [Link](https://openreview.net/pdf?id=xOzlW2vUYc) | [Link](https://github.com/hqh0728/CrossGNN) | NeurIPS'23 | LTSF | -| NLinear | Are Transformers Effective for Time Series Forecasting? | [Link](https://arxiv.org/abs/2205.13504) | [Link](https://github.com/cure-lab/DLinear) | AAAI'23 | LTSF | -| Crossformer | Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting | [Link](https://openreview.net/forum?id=vSVLM2j9eie) | [Link](https://github.com/Thinklab-SJTU/Crossformer) | ICLR'23 | LTSF | -| DLinear | Are Transformers Effective for Time Series Forecasting? | [Link](https://arxiv.org/abs/2205.13504) | [Link](https://github.com/cure-lab/DLinear) | AAAI'23 | LTSF | -| DSformer | A Double Sampling Transformer for Multivariate Time Series Long-term Prediction | [Link](https://arxiv.org/abs/2308.03274) | [Link](https://github.com/ChengqingYu/DSformer) | CIKM'23 | LTSF | -| SegRNN | Segment Recurrent Neural Network for Long-Term Time Series Forecasting | [Link](https://arxiv.org/abs/2308.11200) | [Link](https://github.com/lss-1138/SegRNN) | arXiv | LTSF | -| MTS-Mixers | Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing | [Link](https://arxiv.org/abs/2302.04501) | [Link](https://github.com/plumprc/MTS-Mixers) | arXiv | LTSF | -| LightTS | Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP | [Link](https://arxiv.org/abs/2207.01186) | [Link](https://github.com/thuml/Time-Series-Library/blob/main/models/LightTS.py) | arXiv | LTSF | -| ETSformer | Exponential Smoothing Transformers for Time-series Forecasting | [Link](https://arxiv.org/abs/2202.01381) | [Link](https://github.com/salesforce/ETSformer) | arXiv | LTSF | -| NHiTS | Neural Hierarchical Interpolation for Time Series Forecasting | [Link](https://arxiv.org/abs/2201.12886) | [Link](https://github.com/cchallu/n-hits) | AAAI'23 | LTSF | -| PatchTST | A Time Series is Worth 64 Words: Long-term Forecasting with Transformers | [Link](https://arxiv.org/abs/2211.14730) | [Link](https://github.com/yuqinie98/PatchTST) | ICLR'23 | LTSF | -| TiDE | Long-term Forecasting with TiDE: Time-series Dense Encoder | [Link](https://arxiv.org/abs/2304.08424) | [Link](https://github.com/lich99/TiDE) | TMLR'23 | LTSF | -| TimesNet | Temporal 2D-Variation Modeling for General Time Series Analysis | [Link](https://openreview.net/pdf?id=ju_Uqw384Oq) | [Link](https://github.com/thuml/TimesNet) | ICLR'23 | LTSF | -| Triformer | Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting | [Link](https://arxiv.org/abs/2204.13767) | [Link](https://github.com/razvanc92/triformer) | IJCAI'22 | LTSF | -| NSformer | Exploring the Stationarity in Time Series Forecasting | [Link](https://arxiv.org/abs/2205.14415) | [Link](https://github.com/thuml/Nonstationary_Transformers) | NeurIPS'22 | LTSF | -| FiLM | Frequency improved Legendre Memory Model for LTSF | [Link](https://arxiv.org/abs/2205.08897) | [Link](https://github.com/tianzhou2011/FiLM) | NeurIPS'22 | LTSF | -| FEDformer | Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting | [Link](https://arxiv.org/abs/2201.12740v3) | [Link](https://github.com/MAZiqing/FEDformer) | ICML'22 | LTSF | -| Pyraformer | Low complexity pyramidal Attention For Long-range Time Series Modeling and Forecasting | [Link](https://openreview.net/forum?id=0EXmFzUn5I) | [Link](https://github.com/ant-research/Pyraformer) | ICLR'22 | LTSF | -| HI | Historical Inertia: A Powerful Baseline for Long Sequence Time-series Forecasting | [Link](https://arxiv.org/abs/2103.16349) | None | CIKM'21 | LTSF | -| Autoformer | Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting | [Link](https://arxiv.org/abs/2106.13008) | [Link](https://github.com/thuml/Autoformer) | NeurIPS'21 | LTSF | -| Informer | Beyond Efficient Transformer for Long Sequence Time-Series Forecasting | [Link](https://arxiv.org/abs/2012.07436) | [Link](https://github.com/zhouhaoyi/Informer2020) | AAAI'21 | LTSF |
-

Others

 +| 📊Baseline | 📝Title | 📄Paper | 💻Code | 🏛Venue | 🎯Task | +| :--------- | :------------------------------------------------------------------------ | :--------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------ | :------------------------------------ | +| LightGBM | LightGBM: A Highly Efficient Gradient Boosting Decision Tree | [Link](https://proceedings.neurips.cc/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf) | [Link](https://github.com/microsoft/LightGBM) | NeurIPS'17 | Machine Learning | +| NBeats | Neural basis expansion analysis for interpretable time series forecasting | [Link](https://arxiv.org/abs/1905.10437) | [Link1](https://github.com/ServiceNow/N-BEATS), [Link2](https://github.com/philipperemy/n-beats) | ICLR'19 | Deep Time Series Forecasting | +| DeepAR | Probabilistic Forecasting with Autoregressive Recurrent Networks | [Link](https://arxiv.org/abs/1704.04110) | [Link1](https://github.com/jingw2/demand_forecast), [Link2](https://github.com/husnejahan/DeepAR-pytorch), [Link3](https://github.com/arrigonialberto86/deepar) | Int. J. Forecast'20 | Probabilistic Time Series Forecasting | +| WaveNet | WaveNet: A Generative Model for Raw Audio. | [Link](https://arxiv.org/abs/1609.03499) | [Link 1](https://github.com/JLDeng/ST-Norm/blob/master/models/Wavenet.py), [Link 2](https://github.com/huyouare/WaveNet-Theano) | arXiv | Audio | -| 📊Baseline | 📝Title | 📄Paper | 💻Code | 🏛Venue | 🎯Task | -|:-------------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------|:--------------------------------| -| LightGBM | LightGBM: A Highly Efficient Gradient Boosting Decision Tree | [Link](https://proceedings.neurips.cc/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf) | [Link](https://github.com/microsoft/LightGBM) | NeurIPS'17 | Machine Learning | -| NBeats | Neural basis expansion analysis for interpretable time series forecasting | [Link](https://arxiv.org/abs/1905.10437) | [Link1](https://github.com/ServiceNow/N-BEATS), [Link2](https://github.com/philipperemy/n-beats) | ICLR'19 | Deep Time Series Forecasting | -| DeepAR | Probabilistic Forecasting with Autoregressive Recurrent Networks | [Link](https://arxiv.org/abs/1704.04110) | [Link1](https://github.com/jingw2/demand_forecast), [Link2](https://github.com/husnejahan/DeepAR-pytorch), [Link3](https://github.com/arrigonialberto86/deepar) | Int. J. Forecast'20 | Probabilistic Time Series Forecasting | -| WaveNet | WaveNet: A Generative Model for Raw Audio. | [Link](https://arxiv.org/abs/1609.03499) | [Link 1](https://github.com/JLDeng/ST-Norm/blob/master/models/Wavenet.py), [Link 2](https://github.com/huyouare/WaveNet-Theano) | arXiv | Audio |
- ## 📦 Supported Datasets BasicTS support a variety of datasets, including ***spatial-temporal forecasting***, ***long-term time series forecasting***, and ***large-scale*** datasets. @@ -189,42 +187,44 @@ BasicTS support a variety of datasets, including ***spatial-temporal forecasting

Spatial-Temporal Forecasting

 -| 🏷️Name | 🌐Domain | 📏Length | 📊Time Series Count | 🔄Graph | ⏱️Freq. (m) | 🎯Task | -|:---------|:--------------|-----------:|----------------------:|:--------------------|--------------------:|:---------| -| METR-LA | Traffic Speed | 34272 | 207 | True | 5 | STF | -| PEMS-BAY | Traffic Speed | 52116 | 325 | True | 5 | STF | -| PEMS03 | Traffic Flow | 26208 | 358 | True | 5 | STF | -| PEMS04 | Traffic Flow | 16992 | 307 | True | 5 | STF | -| PEMS07 | Traffic Flow | 28224 | 883 | True | 5 | STF | -| PEMS08 | Traffic Flow | 17856 | 170 | True | 5 | STF | +| 🏷️Name | 🌐Domain | 📏Length | 📊Time Series Count | 🔄Graph | ⏱️Freq. (m) | 🎯Task | +| :------- | :------------ | -------: | ------------------: | :------ | ------------: | :----- | +| METR-LA | Traffic Speed | 34272 | 207 | True | 5 | STF | +| PEMS-BAY | Traffic Speed | 52116 | 325 | True | 5 | STF | +| PEMS03 | Traffic Flow | 26208 | 358 | True | 5 | STF | +| PEMS04 | Traffic Flow | 16992 | 307 | True | 5 | STF | +| PEMS07 | Traffic Flow | 28224 | 883 | True | 5 | STF | +| PEMS08 | Traffic Flow | 17856 | 170 | True | 5 | STF | +

Long-Term Time Series Forecasting

 -| 🏷️Name | 🌐Domain | 📏Length | 📊Time Series Count | 🔄Graph | ⏱️Freq. (m) | 🎯Task | -|:------------------|:------------------------------------|-----------:|----------------------:|:--------------------|--------------------:|:---------| -| BeijingAirQuality | Beijing Air Quality | 36000 | 7 | False | 60 | LTSF | -| ETTh1 | Electricity Transformer Temperature | 14400 | 7 | False | 60 | LTSF | -| ETTh2 | Electricity Transformer Temperature | 14400 | 7 | False | 60 | LTSF | -| ETTm1 | Electricity Transformer Temperature | 57600 | 7 | False | 15 | LTSF | -| ETTm2 | Electricity Transformer Temperature | 57600 | 7 | False | 15 | LTSF | -| Electricity | Electricity Consumption | 26304 | 321 | False | 60 | LTSF | -| ExchangeRate | Exchange Rate | 7588 | 8 | False | 1440 | LTSF | -| Illness | Ilness Data | 966 | 7 | False | 10080 | LTSF | -| Traffic | Road Occupancy Rates | 17544 | 862 | False | 60 | LTSF | -| Weather | Weather | 52696 | 21 | False | 10 | LTSF | +| 🏷️Name | 🌐Domain | 📏Length | 📊Time Series Count | 🔄Graph | ⏱️Freq. (m) | 🎯Task | +| :---------------- | :---------------------------------- | -------: | ------------------: | :------ | ------------: | :----- | +| BeijingAirQuality | Beijing Air Quality | 36000 | 7 | False | 60 | LTSF | +| ETTh1 | Electricity Transformer Temperature | 14400 | 7 | False | 60 | LTSF | +| ETTh2 | Electricity Transformer Temperature | 14400 | 7 | False | 60 | LTSF | +| ETTm1 | Electricity Transformer Temperature | 57600 | 7 | False | 15 | LTSF | +| ETTm2 | Electricity Transformer Temperature | 57600 | 7 | False | 15 | LTSF | +| Electricity | Electricity Consumption | 26304 | 321 | False | 60 | LTSF | +| ExchangeRate | Exchange Rate | 7588 | 8 | False | 1440 | LTSF | +| Illness | Ilness Data | 966 | 7 | False | 10080 | LTSF | +| Traffic | Road Occupancy Rates | 17544 | 862 | False | 60 | LTSF | +| Weather | Weather | 52696 | 21 | False | 10 | LTSF | +

Large Scale Dataset

 -| 🏷️Name | 🌐Domain | 📏Length | 📊Time Series Count | 🔄Graph | ⏱️Freq. (m) | 🎯Task | -|:---------|:-------------|-----------:|----------------------:|:--------------------|--------------------:|:------------| -| CA | Traffic Flow | 35040 | 8600 | True | 15 | Large Scale | -| GBA | Traffic Flow | 35040 | 2352 | True | 15 | Large Scale | -| GLA | Traffic Flow | 35040 | 3834 | True | 15 | Large Scale | -| SD | Traffic Flow | 35040 | 716 | True | 15 | Large Scale | +| 🏷️Name | 🌐Domain | 📏Length | 📊Time Series Count | 🔄Graph | ⏱️Freq. (m) | 🎯Task | +| :------- | :----------- | -------: | ------------------: | :------ | ------------: | :---------- | +| CA | Traffic Flow | 35040 | 8600 | True | 15 | Large Scale | +| GBA | Traffic Flow | 35040 | 2352 | True | 15 | Large Scale | +| GLA | Traffic Flow | 35040 | 3834 | True | 15 | Large Scale | +| SD | Traffic Flow | 35040 | 716 | True | 15 | Large Scale |
@@ -238,8 +238,11 @@ Comprehensive Benchmarking and Heterogeneity Analysis](https://arxiv.org/pdf/231 Thanks goes to these wonderful people ([emoji key](https://allcontributors.org/docs/en/emoji-key)): + + + @@ -264,16 +267,27 @@ Thanks goes to these wonderful people ([emoji key](https://allcontributors.org/d
+ This project follows the [all-contributors](https://github.com/all-contributors/all-contributors) specification. Contributions of any kind welcome! -## Star History +## ⭐ Star History [![Star History Chart](https://api.star-history.com/svg?repos=GestaltCogTeam/BasicTS&type=Date)](https://star-history.com/#GestaltCogTeam/BasicTS&Date) ## 🔗 Acknowledgement BasicTS is developed based on [EasyTorch](https://github.com/cnstark/easytorch), an easy-to-use and powerful open-source neural network training framework. + +## 📧 Contact + +Official Discord Server: + +https://discord.gg/jkjGf9Hz + +Official WeChat Group: + +![wechat](assets/BasicTS-wechat-en.jpg) diff --git a/README_CN.md b/README_CN.md index 797fe95a..3cbfa16e 100644 --- a/README_CN.md +++ b/README_CN.md @@ -6,12 +6,11 @@
-[**English**](./README.md) **|** +[**English**](./README.md) **|** [**简体中文**](./README_CN.md)
- ---
@@ -26,16 +25,16 @@
-🎉 [**快速上手**](./tutorial/getting_started_cn.md) **|** +🎉 [**快速上手**](./tutorial/getting_started_cn.md) **|** 💡 [**总体设计**](./tutorial/overall_design_cn.md) -📦 [**数据集 (Dataset)**](./tutorial/dataset_design_cn.md) **|** -🛠️ [**数据缩放 (Scaler)**](./tutorial/scaler_design_cn.md) **|** -🧠 [**模型约定 (Model)**](./tutorial/model_design_cn.md) **|** +📦 [**数据集 (Dataset)**](./tutorial/dataset_design_cn.md) **|** +🛠️ [**数据缩放 (Scaler)**](./tutorial/scaler_design_cn.md) **|** +🧠 [**模型约定 (Model)**](./tutorial/model_design_cn.md) **|** 📉 [**评估指标 (Metrics)**](./tutorial/metrics_design_cn.md) -🏃‍♂️ [**执行器 (Runner)**](./tutorial/runner_design_cn.md) **|** -📜 [**配置文件 (Config)**](./tutorial/config_design_cn.md) **|** +🏃‍♂️ [**执行器 (Runner)**](./tutorial/runner_design_cn.md) **|** +📜 [**配置文件 (Config)**](./tutorial/config_design_cn.md) **|** 📜 [**基线模型 (Baselines)**](./baselines/)
@@ -50,8 +49,9 @@ BasicTS 一方面通过 **统一且标准化的流程**，为热门的深度学 你可以在[快速上手](./tutorial/getting_started_cn.md)找到详细的教程。另外，我们正在收集 **ToDo** 和 **HowTo**，如果您需要更多功能（例如：更多数据集或基准模型）或教程，欢迎提出 issue 或在[此处](https://github.com/zezhishao/BasicTS/issues/95)留言。 -> [!IMPORTANT] +> [!IMPORTANT] > 如果本项目对您有用，请考虑引用下面的论文: +> > ```LaTeX > @article{shao2023exploring, > title={Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis}, @@ -59,7 +59,8 @@ BasicTS 一方面通过 **统一且标准化的流程**，为热门的深度学 > journal={arXiv preprint arXiv:2310.06119}, > year={2023} > } -> ``` +> ``` +> > 🔥🔥🔥 ***该论文已被IEEE TKDE录用！你可以在这里[查看论文](https://arxiv.org/abs/2310.06119)。*** 🔥🔥🔥 ## ✨ 主要功能亮点 @@ -105,83 +106,81 @@ BasicTS 实现了丰富的基线模型，包括经典模型、时空预测模型

时空预测

 +| 📊Baseline | 📝Title | 📄Paper | 💻Code | 🏛Venue | 🎯Task | +| :--------- | :------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :---------- | :----- | +| BigST | Linear Complexity Spatio-Temporal Graph Neural Network for Traffic Forecasting on Large-Scale Road Networks | [Link](https://dl.acm.org/doi/10.14778/3641204.3641217) | [Link](https://github.com/usail-hkust/BigST?tab=readme-ov-file) | VLDB'24 | STF | +| STDMAE | Spatio-Temporal-Decoupled Masked Pre-training for Traffic Forecasting | [Link](https://arxiv.org/abs/2312.00516) | [Link](https://github.com/Jimmy-7664/STD-MAE) | IJCAI'24 | STF | +| STWave | When Spatio-Temporal Meet Wavelets: Disentangled Traffic Forecasting via Efficient Spectral Graph Attention Networks | [Link](https://ieeexplore.ieee.org/document/10184591) | [Link](https://github.com/LMissher/STWave) | ICDE'23 | STF | +| STAEformer | Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting | [Link](https://arxiv.org/abs/2308.10425) | [Link](https://github.com/XDZhelheim/STAEformer) | CIKM'23 | STF | +| MegaCRN | Spatio-Temporal Meta-Graph Learning for Traffic Forecasting | [Link](https://aps.arxiv.org/abs/2212.05989) | [Link](https://github.com/deepkashiwa20/MegaCRN) | AAAI'23 | STF | +| DGCRN | Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution | [Link](https://arxiv.org/abs/2104.14917) | [Link](https://github.com/tsinghua-fib-lab/Traffic-Benchmark) | ACM TKDD'23 | STF | +| STID | Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting | [Link](https://arxiv.org/abs/2208.05233) | [Link](https://github.com/zezhishao/STID) | CIKM'22 | STF | +| STEP | Pretraining Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting | [Link](https://arxiv.org/abs/2206.09113) | [Link](https://github.com/GestaltCogTeam/STEP?tab=readme-ov-file) | SIGKDD'22 | STF | +| D2STGNN | Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting | [Link](https://arxiv.org/abs/2206.09112) | [Link](https://github.com/zezhishao/D2STGNN) | VLDB'22 | STF | +| STNorm | Spatial and Temporal Normalization for Multi-variate Time Series Forecasting | [Link](https://dl.acm.org/doi/10.1145/3447548.3467330) | [Link](https://github.com/JLDeng/ST-Norm/blob/master/models/Wavenet.py) | SIGKDD'21 | STF | +| STGODE | Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting | [Link](https://arxiv.org/abs/2106.12931) | [Link](https://github.com/square-coder/STGODE) | SIGKDD'21 | STF | +| GTS | Discrete Graph Structure Learning for Forecasting Multiple Time Series | [Link](https://arxiv.org/abs/2101.06861) | [Link](https://github.com/chaoshangcs/GTS) | ICLR'21 | STF | +| StemGNN | Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting | [Link](https://arxiv.org/abs/2103.07719) | [Link](https://github.com/microsoft/StemGNN) | NeurIPS'20 | STF | +| MTGNN | Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks | [Link](https://arxiv.org/abs/2005.11650) | [Link](https://github.com/nnzhan/MTGNN) | SIGKDD'20 | STF | +| AGCRN | Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting | [Link](https://arxiv.org/abs/2007.02842) | [Link](https://github.com/LeiBAI/AGCRN) | NeurIPS'20 | STF | +| GWNet | Graph WaveNet for Deep Spatial-Temporal Graph Modeling | [Link](https://arxiv.org/abs/1906.00121) | [Link](https://github.com/nnzhan/Graph-WaveNet/blob/master/model.py) | IJCAI'19 | STF | +| STGCN | Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting | [Link](https://arxiv.org/abs/1709.04875) | [Link](https://github.com/VeritasYin/STGCN_IJCAI-18) | IJCAI'18 | STF | +| DCRNN | Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting | [Link](https://arxiv.org/abs/1707.01926) | [Link1](https://github.com/chnsh/DCRNN_PyTorch/blob/pytorch_scratch/model/pytorch/dcrnn_cell.py), [Link2](https://github.com/chnsh/DCRNN_PyTorch/blob/pytorch_scratch/model/pytorch/dcrnn_model.py) | ICLR'18 | STF | -| 📊Baseline | 📝Title | 📄Paper | 💻Code | 🏛Venue | 🎯Task | -|:-------------|:---------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------|:---------| -| BigST | Linear Complexity Spatio-Temporal Graph Neural Network for Traffic Forecasting on Large-Scale Road Networks | [Link](https://dl.acm.org/doi/10.14778/3641204.3641217) | [Link](https://github.com/usail-hkust/BigST?tab=readme-ov-file) | VLDB'24 | STF | -| STDMAE | Spatio-Temporal-Decoupled Masked Pre-training for Traffic Forecasting | [Link](https://arxiv.org/abs/2312.00516) | [Link](https://github.com/Jimmy-7664/STD-MAE) | IJCAI'24 | STF | -| STWave | When Spatio-Temporal Meet Wavelets: Disentangled Traffic Forecasting via Efficient Spectral Graph Attention Networks | [Link](https://ieeexplore.ieee.org/document/10184591) | [Link](https://github.com/LMissher/STWave) | ICDE'23 | STF | -| STAEformer | Spatio-Temporal Adaptive Embedding Makes Vanilla Transformer SOTA for Traffic Forecasting | [Link](https://arxiv.org/abs/2308.10425) | [Link](https://github.com/XDZhelheim/STAEformer) | CIKM'23 | STF | -| MegaCRN | Spatio-Temporal Meta-Graph Learning for Traffic Forecasting | [Link](https://aps.arxiv.org/abs/2212.05989) | [Link](https://github.com/deepkashiwa20/MegaCRN) | AAAI'23 | STF | -| DGCRN | Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution | [Link](https://arxiv.org/abs/2104.14917) | [Link](https://github.com/tsinghua-fib-lab/Traffic-Benchmark) | ACM TKDD'23 | STF | -| STID | Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting | [Link](https://arxiv.org/abs/2208.05233) | [Link](https://github.com/zezhishao/STID) | CIKM'22 | STF | -| STEP | Pretraining Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting | [Link](https://arxiv.org/abs/2206.09113) | [Link](https://github.com/GestaltCogTeam/STEP?tab=readme-ov-file) | SIGKDD'22 | STF | -| D2STGNN | Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting | [Link](https://arxiv.org/abs/2206.09112) | [Link](https://github.com/zezhishao/D2STGNN) | VLDB'22 | STF | -| STNorm | Spatial and Temporal Normalization for Multi-variate Time Series Forecasting | [Link](https://dl.acm.org/doi/10.1145/3447548.3467330) | [Link](https://github.com/JLDeng/ST-Norm/blob/master/models/Wavenet.py) | SIGKDD'21 | STF | -| STGODE | Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting | [Link](https://arxiv.org/abs/2106.12931) | [Link](https://github.com/square-coder/STGODE) | SIGKDD'21 | STF | -| GTS | Discrete Graph Structure Learning for Forecasting Multiple Time Series | [Link](https://arxiv.org/abs/2101.06861) | [Link](https://github.com/chaoshangcs/GTS) | ICLR'21 | STF | -| StemGNN | Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting | [Link](https://arxiv.org/abs/2103.07719) | [Link](https://github.com/microsoft/StemGNN) | NeurIPS'20 | STF | -| MTGNN | Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks | [Link](https://arxiv.org/abs/2005.11650) | [Link](https://github.com/nnzhan/MTGNN) | SIGKDD'20 | STF | -| AGCRN | Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting | [Link](https://arxiv.org/abs/2007.02842) | [Link](https://github.com/LeiBAI/AGCRN) | NeurIPS'20 | STF | -| GWNet | Graph WaveNet for Deep Spatial-Temporal Graph Modeling | [Link](https://arxiv.org/abs/1906.00121) | [Link](https://github.com/nnzhan/Graph-WaveNet/blob/master/model.py) | IJCAI'19 | STF | -| STGCN | Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting | [Link](https://arxiv.org/abs/1709.04875) | [Link](https://github.com/VeritasYin/STGCN_IJCAI-18) | IJCAI'18 | STF | -| DCRNN | Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting | [Link](https://arxiv.org/abs/1707.01926) | [Link1](https://github.com/chnsh/DCRNN_PyTorch/blob/pytorch_scratch/model/pytorch/dcrnn_cell.py), [Link2](https://github.com/chnsh/DCRNN_PyTorch/blob/pytorch_scratch/model/pytorch/dcrnn_model.py) | ICLR'18 | STF |

Long-Term Time Series Forecasting

 +| 📊Baseline | 📝Title | 📄Paper | 💻Code | 🏛Venue | 🎯Task | +| :------------ | :------------------------------------------------------------------------------------------------------- | :----------------------------------------------------- | :---------------------------------------------------------------------------- | :--------- | :----- | +| CATS | Are Self-Attentions Effective for Time Series Forecasting? | [Link](https://arxiv.org/pdf/2405.16877) | [Link](https://github.com/dongbeank/CATS) | NeurIPS'24 | LTSF | +| Sumba | Structured Matrix Basis for Multivariate Time Series Forecasting with Interpretable Dynamics | [Link](https://xiucheng.org/assets/pdfs/nips24-sumba.pdf) | [Link](https://github.com/chenxiaodanhit/Sumba/) | NeurIPS'24 | LTSF | +| GLAFF | Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective | [Link](https://arxiv.org/pdf/2409.18696) | [Link](https://github.com/ForestsKing/GLAFF) | NeurIPS'24 | LTSF | +| CycleNet | CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns Forecasting | [Link](https://arxiv.org/pdf/2409.18479) | [Link](https://github.com/ACAT-SCUT/CycleNet) | NeurIPS'24 | LTSF | +| Fredformer | Fredformer: Frequency Debiased Transformer for Time Series Forecasting | [Link](https://arxiv.org/pdf/2406.09009) | [Link](https://github.com/chenzRG/Fredformer) | KDD'24 | LTSF | +| UMixer | An Unet-Mixer Architecture with Stationarity Correction for Time Series Forecasting | [Link](https://arxiv.org/abs/2401.02236) | [Link](https://github.com/XiangMa-Shaun/U-Mixer) | AAAI'24 | LTSF | +| TimeMixer | Decomposable Multiscale Mixing for Time Series Forecasting | [Link](https://arxiv.org/html/2405.14616v1) | [Link](https://github.com/kwuking/TimeMixer) | ICLR'24 | LTSF | +| Time-LLM | Time-LLM: Time Series Forecasting by Reprogramming Large Language Models | [Link](https://arxiv.org/abs/2310.01728) | [Link](https://github.com/KimMeen/Time-LLM) | ICLR'24 | LTSF | +| SparseTSF | Modeling LTSF with 1k Parameters | [Link](https://arxiv.org/abs/2405.00946) | [Link](https://github.com/lss-1138/SparseTSF) | ICML'24 | LTSF | +| iTrainsformer | Inverted Transformers Are Effective for Time Series Forecasting | [Link](https://arxiv.org/abs/2310.06625) | [Link](https://github.com/thuml/iTransformer) | ICLR'24 | LTSF | +| Koopa | Learning Non-stationary Time Series Dynamics with Koopman Predictors | [Link](https://arxiv.org/abs/2305.18803) | [Link](https://github.com/thuml/Koopa) | NeurIPS'24 | LTSF | +| CrossGNN | CrossGNN: Confronting Noisy Multivariate Time Series Via Cross Interaction Refinement | [Link](https://openreview.net/pdf?id=xOzlW2vUYc) | [Link](https://github.com/hqh0728/CrossGNN) | NeurIPS'23 | LTSF | +| NLinear | Are Transformers Effective for Time Series Forecasting? | [Link](https://arxiv.org/abs/2205.13504) | [Link](https://github.com/cure-lab/DLinear) | AAAI'23 | LTSF | +| Crossformer | Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting | [Link](https://openreview.net/forum?id=vSVLM2j9eie) | [Link](https://github.com/Thinklab-SJTU/Crossformer) | ICLR'23 | LTSF | +| DLinear | Are Transformers Effective for Time Series Forecasting? | [Link](https://arxiv.org/abs/2205.13504) | [Link](https://github.com/cure-lab/DLinear) | AAAI'23 | LTSF | +| DSformer | A Double Sampling Transformer for Multivariate Time Series Long-term Prediction | [Link](https://arxiv.org/abs/2308.03274) | [Link](https://github.com/ChengqingYu/DSformer) | CIKM'23 | LTSF | +| SegRNN | Segment Recurrent Neural Network for Long-Term Time Series Forecasting | [Link](https://arxiv.org/abs/2308.11200) | [Link](https://github.com/lss-1138/SegRNN) | arXiv | LTSF | +| MTS-Mixers | Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing | [Link](https://arxiv.org/abs/2302.04501) | [Link](https://github.com/plumprc/MTS-Mixers) | arXiv | LTSF | +| LightTS | Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP | [Link](https://arxiv.org/abs/2207.01186) | [Link](https://github.com/thuml/Time-Series-Library/blob/main/models/LightTS.py) | arXiv | LTSF | +| ETSformer | Exponential Smoothing Transformers for Time-series Forecasting | [Link](https://arxiv.org/abs/2202.01381) | [Link](https://github.com/salesforce/ETSformer) | arXiv | LTSF | +| NHiTS | Neural Hierarchical Interpolation for Time Series Forecasting | [Link](https://arxiv.org/abs/2201.12886) | [Link](https://github.com/cchallu/n-hits) | AAAI'23 | LTSF | +| PatchTST | A Time Series is Worth 64 Words: Long-term Forecasting with Transformers | [Link](https://arxiv.org/abs/2211.14730) | [Link](https://github.com/yuqinie98/PatchTST) | ICLR'23 | LTSF | +| TiDE | Long-term Forecasting with TiDE: Time-series Dense Encoder | [Link](https://arxiv.org/abs/2304.08424) | [Link](https://github.com/lich99/TiDE) | TMLR'23 | LTSF | +| TimesNet | Temporal 2D-Variation Modeling for General Time Series Analysis | [Link](https://openreview.net/pdf?id=ju_Uqw384Oq) | [Link](https://github.com/thuml/TimesNet) | ICLR'23 | LTSF | +| Triformer | Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting | [Link](https://arxiv.org/abs/2204.13767) | [Link](https://github.com/razvanc92/triformer) | IJCAI'22 | LTSF | +| NSformer | Exploring the Stationarity in Time Series Forecasting | [Link](https://arxiv.org/abs/2205.14415) | [Link](https://github.com/thuml/Nonstationary_Transformers) | NeurIPS'22 | LTSF | +| FiLM | Frequency improved Legendre Memory Model for LTSF | [Link](https://arxiv.org/abs/2205.08897) | [Link](https://github.com/tianzhou2011/FiLM) | NeurIPS'22 | LTSF | +| FEDformer | Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting | [Link](https://arxiv.org/abs/2201.12740v3) | [Link](https://github.com/MAZiqing/FEDformer) | ICML'22 | LTSF | +| Pyraformer | Low complexity pyramidal Attention For Long-range Time Series Modeling and Forecasting | [Link](https://openreview.net/forum?id=0EXmFzUn5I) | [Link](https://github.com/ant-research/Pyraformer) | ICLR'22 | LTSF | +| HI | Historical Inertia: A Powerful Baseline for Long Sequence Time-series Forecasting | [Link](https://arxiv.org/abs/2103.16349) | None | CIKM'21 | LTSF | +| Autoformer | Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting | [Link](https://arxiv.org/abs/2106.13008) | [Link](https://github.com/thuml/Autoformer) | NeurIPS'21 | LTSF | +| Informer | Beyond Efficient Transformer for Long Sequence Time-Series Forecasting | [Link](https://arxiv.org/abs/2012.07436) | [Link](https://github.com/zhouhaoyi/Informer2020) | AAAI'21 | LTSF | -| 📊Baseline | 📝Title | 📄Paper | 💻Code | 🏛Venue | 🎯Task | -|:--------------|:------------------------------------------------------------------------------------------------|:----------------------------------------------------|:---------------------------------------------------------------------------------|:-----------|:---------| -| CATS | Are Self-Attentions Effective for Time Series Forecasting? | [Link]( https://arxiv.org/pdf/2405.16877) | [Link](https://github.com/dongbeank/CATS) | NeurIPS'24 | LTSF | -| Sumba | Structured Matrix Basis for Multivariate Time Series Forecasting with Interpretable Dynamics | [Link]( https://xiucheng.org/assets/pdfs/nips24-sumba.pdf) | [Link](https://github.com/chenxiaodanhit/Sumba/) | NeurIPS'24 | LTSF | -| GLAFF | Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective | [Link]( https://arxiv.org/pdf/2409.18696) | [Link](https://github.com/ForestsKing/GLAFF) | NeurIPS'24 | LTSF | -| CycleNet | CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns Forecasting | [Link]( https://arxiv.org/pdf/2409.18479) | [Link](https://github.com/ACAT-SCUT/CycleNet) | NeurIPS'24 | LTSF | -| Fredformer | Fredformer: Frequency Debiased Transformer for Time Series Forecasting | [Link]( https://arxiv.org/pdf/2406.09009) | [Link](https://github.com/chenzRG/Fredformer) | KDD'24 | LTSF | -| UMixer | An Unet-Mixer Architecture with Stationarity Correction for Time Series Forecasting | [Link](https://arxiv.org/abs/2401.02236) | [Link](https://github.com/XiangMa-Shaun/U-Mixer) | AAAI'24 | LTSF | -| TimeMixer | Decomposable Multiscale Mixing for Time Series Forecasting | [Link](https://arxiv.org/html/2405.14616v1) | [Link](https://github.com/kwuking/TimeMixer) | ICLR'24 | LTSF | -| Time-LLM | Time-LLM: Time Series Forecasting by Reprogramming Large Language Models | [Link](https://arxiv.org/abs/2310.01728) | [Link](https://github.com/KimMeen/Time-LLM) | ICLR'24 | LTSF | -| SparseTSF | Modeling LTSF with 1k Parameters | [Link](https://arxiv.org/abs/2405.00946) | [Link](https://github.com/lss-1138/SparseTSF) | ICML'24 | LTSF | -| iTrainsformer | Inverted Transformers Are Effective for Time Series Forecasting | [Link](https://arxiv.org/abs/2310.06625) | [Link](https://github.com/thuml/iTransformer) | ICLR'24 | LTSF | -| Koopa | Learning Non-stationary Time Series Dynamics with Koopman Predictors | [Link](https://arxiv.org/abs/2305.18803) | [Link](https://github.com/thuml/Koopa) | NeurIPS'24 | LTSF | -| CrossGNN | CrossGNN: Confronting Noisy Multivariate Time Series Via Cross Interaction Refinement | [Link](https://openreview.net/pdf?id=xOzlW2vUYc) | [Link](https://github.com/hqh0728/CrossGNN) | NeurIPS'23 | LTSF | -| NLinear | Are Transformers Effective for Time Series Forecasting? | [Link](https://arxiv.org/abs/2205.13504) | [Link](https://github.com/cure-lab/DLinear) | AAAI'23 | LTSF | -| Crossformer | Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting | [Link](https://openreview.net/forum?id=vSVLM2j9eie) | [Link](https://github.com/Thinklab-SJTU/Crossformer) | ICLR'23 | LTSF | -| DLinear | Are Transformers Effective for Time Series Forecasting? | [Link](https://arxiv.org/abs/2205.13504) | [Link](https://github.com/cure-lab/DLinear) | AAAI'23 | LTSF | -| DSformer | A Double Sampling Transformer for Multivariate Time Series Long-term Prediction | [Link](https://arxiv.org/abs/2308.03274) | [Link](https://github.com/ChengqingYu/DSformer) | CIKM'23 | LTSF | -| SegRNN | Segment Recurrent Neural Network for Long-Term Time Series Forecasting | [Link](https://arxiv.org/abs/2308.11200) | [Link](https://github.com/lss-1138/SegRNN) | arXiv | LTSF | -| MTS-Mixers | Multivariate Time Series Forecasting via Factorized Temporal and Channel Mixing | [Link](https://arxiv.org/abs/2302.04501) | [Link](https://github.com/plumprc/MTS-Mixers) | arXiv | LTSF | -| LightTS | Fast Multivariate Time Series Forecasting with Light Sampling-oriented MLP | [Link](https://arxiv.org/abs/2207.01186) | [Link](https://github.com/thuml/Time-Series-Library/blob/main/models/LightTS.py) | arXiv | LTSF | -| ETSformer | Exponential Smoothing Transformers for Time-series Forecasting | [Link](https://arxiv.org/abs/2202.01381) | [Link](https://github.com/salesforce/ETSformer) | arXiv | LTSF | -| NHiTS | Neural Hierarchical Interpolation for Time Series Forecasting | [Link](https://arxiv.org/abs/2201.12886) | [Link](https://github.com/cchallu/n-hits) | AAAI'23 | LTSF | -| PatchTST | A Time Series is Worth 64 Words: Long-term Forecasting with Transformers | [Link](https://arxiv.org/abs/2211.14730) | [Link](https://github.com/yuqinie98/PatchTST) | ICLR'23 | LTSF | -| TiDE | Long-term Forecasting with TiDE: Time-series Dense Encoder | [Link](https://arxiv.org/abs/2304.08424) | [Link](https://github.com/lich99/TiDE) | TMLR'23 | LTSF | -| TimesNet | Temporal 2D-Variation Modeling for General Time Series Analysis | [Link](https://openreview.net/pdf?id=ju_Uqw384Oq) | [Link](https://github.com/thuml/TimesNet) | ICLR'23 | LTSF | -| Triformer | Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting | [Link](https://arxiv.org/abs/2204.13767) | [Link](https://github.com/razvanc92/triformer) | IJCAI'22 | LTSF | -| NSformer | Exploring the Stationarity in Time Series Forecasting | [Link](https://arxiv.org/abs/2205.14415) | [Link](https://github.com/thuml/Nonstationary_Transformers) | NeurIPS'22 | LTSF | -| FiLM | Frequency improved Legendre Memory Model for LTSF | [Link](https://arxiv.org/abs/2205.08897) | [Link](https://github.com/tianzhou2011/FiLM) | NeurIPS'22 | LTSF | -| FEDformer | Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting | [Link](https://arxiv.org/abs/2201.12740v3) | [Link](https://github.com/MAZiqing/FEDformer) | ICML'22 | LTSF | -| Pyraformer | Low complexity pyramidal Attention For Long-range Time Series Modeling and Forecasting | [Link](https://openreview.net/forum?id=0EXmFzUn5I) | [Link](https://github.com/ant-research/Pyraformer) | ICLR'22 | LTSF | -| HI | Historical Inertia: A Powerful Baseline for Long Sequence Time-series Forecasting | [Link](https://arxiv.org/abs/2103.16349) | None | CIKM'21 | LTSF | -| Autoformer | Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting | [Link](https://arxiv.org/abs/2106.13008) | [Link](https://github.com/thuml/Autoformer) | NeurIPS'21 | LTSF | -| Informer | Beyond Efficient Transformer for Long Sequence Time-Series Forecasting | [Link](https://arxiv.org/abs/2012.07436) | [Link](https://github.com/zhouhaoyi/Informer2020) | AAAI'21 | LTSF |
-

其他方法

 +| 📊Baseline | 📝Title | 📄Paper | 💻Code | 🏛Venue | 🎯Task | +| :--------- | :------------------------------------------------------------------------ | :--------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------ | :------------------------------------ | +| LightGBM | LightGBM: A Highly Efficient Gradient Boosting Decision Tree | [Link](https://proceedings.neurips.cc/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf) | [Link](https://github.com/microsoft/LightGBM) | NeurIPS'17 | Machine Learning | +| NBeats | Neural basis expansion analysis for interpretable time series forecasting | [Link](https://arxiv.org/abs/1905.10437) | [Link1](https://github.com/ServiceNow/N-BEATS), [Link2](https://github.com/philipperemy/n-beats) | ICLR'19 | Deep Time Series Forecasting | +| DeepAR | Probabilistic Forecasting with Autoregressive Recurrent Networks | [Link](https://arxiv.org/abs/1704.04110) | [Link1](https://github.com/jingw2/demand_forecast), [Link2](https://github.com/husnejahan/DeepAR-pytorch), [Link3](https://github.com/arrigonialberto86/deepar) | Int. J. Forecast'20 | Probabilistic Time Series Forecasting | +| WaveNet | WaveNet: A Generative Model for Raw Audio. | [Link](https://arxiv.org/abs/1609.03499) | [Link 1](https://github.com/JLDeng/ST-Norm/blob/master/models/Wavenet.py), [Link 2](https://github.com/huyouare/WaveNet-Theano) | arXiv | Audio | -| 📊Baseline | 📝Title | 📄Paper | 💻Code | 🏛Venue | 🎯Task | -|:-------------|:----------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------|:--------------------|:--------------------------------| -| LightGBM | LightGBM: A Highly Efficient Gradient Boosting Decision Tree | [Link](https://proceedings.neurips.cc/paper/2017/file/6449f44a102fde848669bdd9eb6b76fa-Paper.pdf) | [Link](https://github.com/microsoft/LightGBM) | NeurIPS'17 | Machine Learning | -| NBeats | Neural basis expansion analysis for interpretable time series forecasting | [Link](https://arxiv.org/abs/1905.10437) | [Link1](https://github.com/ServiceNow/N-BEATS), [Link2](https://github.com/philipperemy/n-beats) | ICLR'19 | Deep Time Series Forecasting | -| DeepAR | Probabilistic Forecasting with Autoregressive Recurrent Networks | [Link](https://arxiv.org/abs/1704.04110) | [Link1](https://github.com/jingw2/demand_forecast), [Link2](https://github.com/husnejahan/DeepAR-pytorch), [Link3](https://github.com/arrigonialberto86/deepar) | Int. J. Forecast'20 | Probabilistic Time Series Forecasting | -| WaveNet | WaveNet: A Generative Model for Raw Audio. | [Link](https://arxiv.org/abs/1609.03499) | [Link 1](https://github.com/JLDeng/ST-Norm/blob/master/models/Wavenet.py), [Link 2](https://github.com/huyouare/WaveNet-Theano) | arXiv | Audio |
- ## 📦 支持的数据集 BasicTS 支持多种类型的数据集，涵盖时空预测、长序列预测及大规模数据集。 @@ -189,42 +188,44 @@ BasicTS 支持多种类型的数据集，涵盖时空预测、长序列预测及

时空预测

 -| 🏷️Name | 🌐Domain | 📏Length | 📊Time Series Count | 🔄Graph | ⏱️Freq. (m) | 🎯Task | -|:---------|:--------------|-----------:|----------------------:|:--------------------|--------------------:|:---------| -| METR-LA | Traffic Speed | 34272 | 207 | True | 5 | STF | -| PEMS-BAY | Traffic Speed | 52116 | 325 | True | 5 | STF | -| PEMS03 | Traffic Flow | 26208 | 358 | True | 5 | STF | -| PEMS04 | Traffic Flow | 16992 | 307 | True | 5 | STF | -| PEMS07 | Traffic Flow | 28224 | 883 | True | 5 | STF | -| PEMS08 | Traffic Flow | 17856 | 170 | True | 5 | STF | +| 🏷️Name | 🌐Domain | 📏Length | 📊Time Series Count | 🔄Graph | ⏱️Freq. (m) | 🎯Task | +| :------- | :------------ | -------: | ------------------: | :------ | ------------: | :----- | +| METR-LA | Traffic Speed | 34272 | 207 | True | 5 | STF | +| PEMS-BAY | Traffic Speed | 52116 | 325 | True | 5 | STF | +| PEMS03 | Traffic Flow | 26208 | 358 | True | 5 | STF | +| PEMS04 | Traffic Flow | 16992 | 307 | True | 5 | STF | +| PEMS07 | Traffic Flow | 28224 | 883 | True | 5 | STF | +| PEMS08 | Traffic Flow | 17856 | 170 | True | 5 | STF | +

长序列预测

 -| 🏷️Name | 🌐Domain | 📏Length | 📊Time Series Count | 🔄Graph | ⏱️Freq. (m) | 🎯Task | -|:------------------|:------------------------------------|-----------:|----------------------:|:--------------------|--------------------:|:---------| -| BeijingAirQuality | Beijing Air Quality | 36000 | 7 | False | 60 | LTSF | -| ETTh1 | Electricity Transformer Temperature | 14400 | 7 | False | 60 | LTSF | -| ETTh2 | Electricity Transformer Temperature | 14400 | 7 | False | 60 | LTSF | -| ETTm1 | Electricity Transformer Temperature | 57600 | 7 | False | 15 | LTSF | -| ETTm2 | Electricity Transformer Temperature | 57600 | 7 | False | 15 | LTSF | -| Electricity | Electricity Consumption | 26304 | 321 | False | 60 | LTSF | -| ExchangeRate | Exchange Rate | 7588 | 8 | False | 1440 | LTSF | -| Illness | Ilness Data | 966 | 7 | False | 10080 | LTSF | -| Traffic | Road Occupancy Rates | 17544 | 862 | False | 60 | LTSF | -| Weather | Weather | 52696 | 21 | False | 10 | LTSF | +| 🏷️Name | 🌐Domain | 📏Length | 📊Time Series Count | 🔄Graph | ⏱️Freq. (m) | 🎯Task | +| :---------------- | :---------------------------------- | -------: | ------------------: | :------ | ------------: | :----- | +| BeijingAirQuality | Beijing Air Quality | 36000 | 7 | False | 60 | LTSF | +| ETTh1 | Electricity Transformer Temperature | 14400 | 7 | False | 60 | LTSF | +| ETTh2 | Electricity Transformer Temperature | 14400 | 7 | False | 60 | LTSF | +| ETTm1 | Electricity Transformer Temperature | 57600 | 7 | False | 15 | LTSF | +| ETTm2 | Electricity Transformer Temperature | 57600 | 7 | False | 15 | LTSF | +| Electricity | Electricity Consumption | 26304 | 321 | False | 60 | LTSF | +| ExchangeRate | Exchange Rate | 7588 | 8 | False | 1440 | LTSF | +| Illness | Ilness Data | 966 | 7 | False | 10080 | LTSF | +| Traffic | Road Occupancy Rates | 17544 | 862 | False | 60 | LTSF | +| Weather | Weather | 52696 | 21 | False | 10 | LTSF | +

大规模数据集

 -| 🏷️Name | 🌐Domain | 📏Length | 📊Time Series Count | 🔄Graph | ⏱️Freq. (m) | 🎯Task | -|:---------|:-------------|-----------:|----------------------:|:--------------------|--------------------:|:------------| -| CA | Traffic Flow | 35040 | 8600 | True | 15 | Large Scale | -| GBA | Traffic Flow | 35040 | 2352 | True | 15 | Large Scale | -| GLA | Traffic Flow | 35040 | 3834 | True | 15 | Large Scale | -| SD | Traffic Flow | 35040 | 716 | True | 15 | Large Scale | +| 🏷️Name | 🌐Domain | 📏Length | 📊Time Series Count | 🔄Graph | ⏱️Freq. (m) | 🎯Task | +| :------- | :----------- | -------: | ------------------: | :------ | ------------: | :---------- | +| CA | Traffic Flow | 35040 | 8600 | True | 15 | Large Scale | +| GBA | Traffic Flow | 35040 | 2352 | True | 15 | Large Scale | +| GLA | Traffic Flow | 35040 | 3834 | True | 15 | Large Scale | +| SD | Traffic Flow | 35040 | 716 | True | 15 | Large Scale |
@@ -237,8 +238,11 @@ BasicTS 支持多种类型的数据集，涵盖时空预测、长序列预测及 感谢这些优秀的贡献者们 ([表情符号指南](https://allcontributors.org/docs/en/emoji-key))： + + + @@ -263,16 +267,27 @@ BasicTS 支持多种类型的数据集，涵盖时空预测、长序列预测及
+ 此项目遵循 [all-contributors](https://github.com/all-contributors/all-contributors) 规范。欢迎任何形式的贡献！ -## Star History +## ⭐ Star History [![Star History Chart](https://api.star-history.com/svg?repos=GestaltCogTeam/BasicTS&type=Date)](https://star-history.com/#GestaltCogTeam/BasicTS&Date) ## 🔗 致谢 BasicTS 是基于 [EasyTorch](https://github.com/cnstark/easytorch) 开发的，这是一个易于使用且功能强大的开源神经网络训练框架。 + +## 📧 联系我们 + +官方Discord Server: + +https://discord.gg/jkjGf9Hz + +官方微信群: + +![wechat](assets/BasicTS-wechat-cn.jpg) diff --git a/assets/BasicTS-wechat-cn.jpg b/assets/BasicTS-wechat-cn.jpg new file mode 100644 index 00000000..58768de7 Binary files /dev/null and b/assets/BasicTS-wechat-cn.jpg differ diff --git a/assets/BasicTS-wechat-en.jpg b/assets/BasicTS-wechat-en.jpg new file mode 100644 index 00000000..d7b0a407 Binary files /dev/null and b/assets/BasicTS-wechat-en.jpg differ