https://github.com/DAMO-DI-ML/KDD2022-Quatformer
Source code of KDD'22 paper: Learning to Rotate: Quaternion Transformer for Complicated Periodical Time Series Forecasting
https://github.com/DAMO-DI-ML/KDD2022-Quatformer
Last synced: 5 days ago
JSON representation
Source code of KDD'22 paper: Learning to Rotate: Quaternion Transformer for Complicated Periodical Time Series Forecasting
- Host: GitHub
- URL: https://github.com/DAMO-DI-ML/KDD2022-Quatformer
- Owner: DAMO-DI-ML
- License: mit
- Created: 2022-10-27T13:48:37.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2023-05-12T14:12:44.000Z (almost 2 years ago)
- Last Synced: 2024-11-13T10:37:56.066Z (6 months ago)
- Language: Python
- Size: 37.1 KB
- Stars: 27
- Watchers: 4
- Forks: 5
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-AI-for-time-series-papers - \[code\
README
# Quatformer (KDD 2022 paper)
* Weiqi Chen, Wenwei Wang, Bingqing Peng, Qingsong Wen, Tian Zhou, Liang Sun, "Learning to Rotate: Quaternion Transformer for Complicated Periodical Time Series Forecasting" in Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2022), 2022. [[paper](https://dl.acm.org/doi/abs/10.1145/3534678.3539234)]
Quaternion Transformer (Quatformer) introduce quternion to model complicated periodical patterns (i.e., muliple periods, variable periods, and phase shift) in time series which also has a linear complexity with decoupling attention. Our empirical studies with six benchmark datasets verify its effectiveness.
## Get Started
1. Install Python 3.6, PyTorch 1.9.0.
2. Install other dependencies by:
```shell
pip install -r requirements.txt
```
3. Download data. You can obtain all the six benchmarks from [[Autoformer](https://github.com/thuml/Autoformer)] or [[Informer](https://github.com/zhouhaoyi/Informer2020)].
4. Train the model. We provide the experiment scripts of all benchmarks under the folder `./scripts`. You can reproduce the experiment results by:
```bash
bash ./scripts/ETT_script/Quatformer.sh
bash ./scripts/ECL_script/Quatformer.sh
bash ./scripts/Exchange_script/Quatformer.sh
bash ./scripts/Traffic_script/Quatformer.sh
bash ./scripts/Weather_script/Quatformer.sh
bash ./scripts/ILI_script/Quatformer.sh
```
## Citation
If you find this repo useful, please cite our paper.
```
@inproceedings{chen2022quatformer,
title={Learning to Rotate: Quaternion Transformer for Complicated Periodical Time Series Forecasting},
author={Chen, Weiqi and Wang, Wenwei and Peng, Bingqing and Wen, Qingsong and Zhou, Tian and Sun, Liang},
booktitle={Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining},
pages={146--156},
year={2022}
}
```
## Contact
If you have any question or want to use the code, please contact [email protected].
## Acknowledgement
We appreciate the following github repos a lot for their valuable code base or datasets:
https://github.com/thuml/Autoformer
https://github.com/zhouhaoyi/Informer2020
https://github.com/zhouhaoyi/ETDataset
https://github.com/laiguokun/multivariate-time-series-data