Fourier Basis Mapping: A Time-Frequency Learning Framework for Time Series Forecasting

This is the expanding work from the original paper "Rethinking Fourier Transform from A Basis Functions Perspective for Long-term Time Series Forecasting." (NeurIPS 2024) to a journal. Please give a star to support this repository if you like it. Many thanks!

This is the offical implementation of FBM-S model.

🚀 Implement the project

1. Install requirements. pip install -r requirements.txt

2. Download data. You can download the ETTh1, ETTh2, ETTm1, ETTm2, Electricity and Traffic data from Autoformer and WTH data from Google Drive The other datasets can be download at Baidu Drive. Create a seperate folder ./dataset and put all the csv files in the directory.

3. Training. All the scripts are in the directory ./scripts/long_term_forecast/file_to_implement.sh and ./scripts/short_term_forecast/file_to_implement.sh

sh ./scripts/long_term_forecast/ETTh1.sh
sh ./scripts/short_term_forecast/PEMS.sh

You can adjust the hyperparameters based on your needs. Notably, our method requires a smaller learning rate due to the decomposition of values, and the learning rate adjustment strategy 'TST' has been excluded for Long-term TSF.

📰 News: The training loss has been changed from L2 to L1 for better performance.

📰 News: Standardization on the PEMS datasets has been removed for better performance, and intercept information has been added to the trend block.

🧠 Fourier Basis Mapping

📚 Acknowledgement

We appreciate the following github repo very much for the valuable code base and datasets:

https://github.com/cure-lab/LTSF-Linear

https://github.com/zhouhaoyi/Informer2020

https://github.com/thuml/Autoformer

https://github.com/MAZiqing/FEDformer

https://github.com/alipay/Pyraformer

https://github.com/yuqinie98/PatchTST

https://github.com/ServiceNow/N-BEATS

https://github.com/aikunyi/FreTS

https://github.com/hqh0728/CrossGNN

https://github.com/thuml/iTransformer

https://github.com/kwuking/TimeMixer

https://github.com/VEWOXIC/FITS

https://github.com/decisionintelligence/DUET

Citation

If you find this repository useful, please consider citing our paper. If you have any questions, feel free to contact: runze.y@sjtu.edu.cn