FEDformer (ICML 2022 paper)

Tian Zhou, Ziqing Ma, Qingsong Wen, Xue Wang, Liang Sun, Rong Jin, "FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting," in Proc. 39th International Conference on Machine Learning (ICML 2022), Baltimore, Maryland, July 17-23, 2022

Frequency Enhanced Decomposed Transformer (FEDformer) is more efficient than standard Transformer with a linear complexity to the sequence length [paper].

Our empirical studies with six benchmark datasets show that compared with state-of-the-art methods, FEDformer can reduce prediction error by 14.8% and 22.6% for multivariate and univariate time series, respectively.

Frequency Enhanced Attention

Figure 1. Overall structure of FEDformer
image image
Figure 2. Frequency Enhanced Block (FEB) Figure 3. Frequency Enhanced Attention (FEA)

Main Results


Get Started

  1. Install Python>=3.8, PyTorch 1.9.0.
  2. Download data. You can obtain all the six benchmarks from [Autoformer] or [Informer].
  3. Train the model. We provide the experiment scripts of all benchmarks under the folder ./scripts. You can reproduce the multivariate and univariate experiment results by running the following shell code separately:
bash ./scripts/run_M.sh
bash ./scripts/run_S.sh


If you find this repo useful, please cite our paper.

  title={{FEDformer}: Frequency enhanced decomposed transformer for long-term series forecasting},
  author={Zhou, Tian and Ma, Ziqing and Wen, Qingsong and Wang, Xue and Sun, Liang and Jin, Rong},
  booktitle={Proc. 39th International Conference on Machine Learning (ICML 2022)},
  location = {Baltimore, Maryland},

Further Reading

Survey on Transformers in Time Series:

Qingsong Wen, Tian Zhou, Chaoli Zhang, Weiqi Chen, Ziqing Ma, Junchi Yan, and Liang Sun. "Transformers in time series: A survey." arXiv preprint arXiv:2202.07125 (2022). paper


If you have any question or want to use the code, please contact [email protected] or [email protected] .


We appreciate the following github repos a lot for their valuable code base or datasets:





Get A Weekly Email With Trending Projects For These Categories
No Spam. Unsubscribe easily at any time.