Skip to content

Mingyue-Cheng/FormerTime

 
 

Repository files navigation

FormerTime: Hierarchical Multi-scale Representation for Multivariate Time Series Classification (WWW2023)


🙋 Please let us know if you find out a mistake or have any suggestions!

🌟 If you find this resource helpful, please consider to star this repository and cite our research:

@inproceedings{cheng2023formertime,
  title={Formertime: Hierarchical multi-scale representations for multivariate time series classification},
  author={Cheng, Mingyue and Liu, Qi and Liu, Zhiding and Li, Zhi and Luo, Yucong and Chen, Enhong},
  booktitle={Proceedings of the ACM Web Conference 2023},
  pages={1437--1445},
  year={2023}
}

Requirements


  • pytorch 1.x
  • pandas
  • numpy
  • tqdm

Usage


sh run.sh

For more detailed params, please refer to args.py

Further Reading

1, Convtimenet: A deep hierarchical fully convolutional model for multivariate time series analysis. Authors: Cheng, Mingyue and Yang, Jiqian and Pan, Tingyue and Liu, Qi and Li, Zhi

@article{cheng2024convtimenet,
  title={Convtimenet: A deep hierarchical fully convolutional model for multivariate time series analysis},
  author={Cheng, Mingyue and Yang, Jiqian and Pan, Tingyue and Liu, Qi and Li, Zhi},
  journal={arXiv preprint arXiv:2403.01493},
  year={2024}
}

2, InstructTime: Advancing Time Series Classification with Multimodal Language Modeling. Authors: Cheng, Mingyue and Chen, Yiheng and Liu, Qi and Liu, Zhiding and Luo, Yucong

@article{cheng2024advancing,
  title={Advancing Time Series Classification with Multimodal Language Modeling},
  author={Cheng, Mingyue and Chen, Yiheng and Liu, Qi and Liu, Zhiding and Luo, Yucong},
  journal={arXiv preprint arXiv:2403.12371},
  year={2024}
}

3, TimeMAE: Self-supervised Representation of Time Series with Decoupled Masked Autoencoders. Authors: Mingyue Cheng, Qi Liu*, Zhiding Liu, Hao Zhang, Rujiao Zhang, Enhong Chen

@article{cheng2023timemae,
  title={Timemae: Self-supervised representations of time series with decoupled masked autoencoders},
  author={Cheng, Mingyue and Liu, Qi and Liu, Zhiding and Zhang, Hao and Zhang, Rujiao and Chen, Enhong},
  journal={arXiv preprint arXiv:2303.00320},
  year={2023}
}

4, CrossTimeNet: Learning Transferable Time Series Classifier with Cross-Domain Pre-training from Language Model. Authors: Cheng, Mingyue and Tao, Xiaoyu and Liu, Qi and Zhang, Hao and Chen, Yiheng and Lei, Chenyi

@article{cheng2024learning,
  title={Learning Transferable Time Series Classifier with Cross-Domain Pre-training from Language Model},
  author={Cheng, Mingyue and Tao, Xiaoyu and Liu, Qi and Zhang, Hao and Chen, Yiheng and Lei, Chenyi},
  journal={arXiv preprint arXiv:2403.12372},
  year={2024}
}

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 98.1%
  • Shell 1.9%