Multi-resolution Time-Series Transformer for Long-term Forecasting (MTST). arxiv
This paper has been accepted at AISTATS 2024.
-
Install requirements.
pip install -r requirements.txt
-
Download data. You can download all the datasets from Autoformer. Create a seperate folder
./dataset
and put all the csv files in the directory.
- Training. All the scripts are in the directory
./scripts/MTST
. For example,
sh ./scripts/MTST/etth2.sh
We appreciate the following github repo very much for the valuable code base and datasets:
https://github.com/yuqinie98/PatchTST
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