Skip to content

The code for Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing Values.

Notifications You must be signed in to change notification settings

chenxiaodanhit/BiTGraph

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

61 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

BiTGraph (ICLR 2024)

The code for paper: Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing Values.

Getting Start

  1. Install requirements. pip install -r requirements.txt
  2. Download data.

Download Metr-LA, ETTh1, Electricity, PEMS datasets from here. Obtain BeijingAir dataset from Brits. Put all the files in the ./data.

  1. Training.

python main.py --epochs 200 --mask_ratio 0.2 --dataset-name Metr

  1. Testing.

python test_forecasting.py --epochs 200 --mask_ratio 0.2 --dataset-name Metr

Citation

@inproceedings{BiTGraph, 
  title={Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing Values},
  author={Chen, Xiaodan and Li, Xiucheng and Liu, Bo and Li, Zhijun},
  booktitle={International Conference on Learning Representations (ICLR)},
  year={2024}
}

About

The code for Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing Values.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages