Home

Awesome

<div align="center">

VisionTS

Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters

Paper PyPI - Version

</div> <p align="center"> 🔍&nbsp;<a href="#-about">About</a> | 🚀&nbsp;<a href="#-quick-start">Quick Start</a> | 📊&nbsp;<a href="#-evaluation">Evaluation</a> | 🔗&nbsp;<a href="#-citation">Citation</a> </p>

🔍 About

<div align="center"> <img src="figure/ltsf_performance_overview.png" style="width:70%;" /> </div> <div align="center"> <img src="figure/method.png" style="width: 70%;" /> </div>

🚀 Quick Start

We have uploaded our package to PyPI. Please first install pytorch, then running the following command for installing VisionTS:

pip install visionts

Then, you can refer to demo.ipynb about forecasting time series using VisionTS, with a clear visualization of the image reconstruction.

📊 Evaluation

Our repository is built on Time-Series-Library, MAE, and GluonTS. Please install the dependencies through requirements.txt before running the evaluation.

Long-Term TSF Benchmarks (Zero-Shot)

<div align="center"> <img src="figure/ltsf_performance.png" style="width: 70%;" /> </div>

We evaluate our methods on 6 long-term TSF benchmarks for zero-shot forecasting. The scripts are under long_term_tsf/scripts/vision_ts_zeroshot. Before running, you should first follow the instructions of Time-Series-Library to download datasets into long_term_tsf/dataset. Using the following command for reproduction:

cd long_term_tsf/
bash scripts/vision_ts_zeroshot/$SOME_DATASET.sh

Monash (Zero-Shot)

<div align="center"> <img src="figure/monash_performance.png" style="width: 50%;" /> </div>

We evaluate our methods on 29 Monash TSF benchmarks. You can use the following command for reproduction, where the benchmarks will be automatically downloaded.

cd eval_gluonts/
bash run_monash.sh

[!IMPORTANT] The results in the paper are evaluated based on python==3.8.18, torch==1.7.1, torchvision==0.8.2, and timm==0.3.2. Different versions may lead to slightly different performance.

PF (Zero-Shot)

We evaluate our methods on 6 long-term TSF benchmarks for zero-shot forecasting. Before running, you should first follow the instructions of Time-Series-Library to download datasets into long_term_tsf/dataset, in addition to the following three datasets:

You can use the following command for reproduction.

cd eval_gluonts/
bash run_pf.sh

Long-Term TSF Benchmarks (Full-Shot)

We evaluate our methods on 8 long-term TSF benchmarks for full-shot forecasting. The scripts are under long_term_tsf/scripts/vision_ts_fullshot. Using the following command for reproduction:

cd long_term_tsf/
bash scripts/vision_ts_fullshot/$SOME_DATASET.sh

🔗 Citation

@misc{chen2024visionts,
      title={VisionTS: Visual Masked Autoencoders Are Free-Lunch Zero-Shot Time Series Forecasters}, 
      author={Mouxiang Chen and Lefei Shen and Zhuo Li and Xiaoyun Joy Wang and Jianling Sun and Chenghao Liu},
      year={2024},
      eprint={2408.17253},
      archivePrefix={arXiv},
      url={https://arxiv.org/abs/2408.17253}, 
}

⭐ Star History

<div align="center"> <a href="https://star-history.com/#Keytoyze/VisionTS&Timeline"> <img src="https://api.star-history.com/svg?repos=Keytoyze/VisionTS&type=Timeline" style="width: 70%;" /> </a> </div>