Skip to content

Code for "Understanding and Simplifying Architecture Search in Spatio-Temporal Graph Neural Networks" accepted by TMLR 2023

Notifications You must be signed in to change notification settings

LARS-research/SimpleSTG

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 

Repository files navigation

This is the code for our publication "Understanding and Simplifying Architecture Search in Spatio-Temporal Graph Neural Networks" accepted by Transactions on Machine Learning Research (TMLR) 2023.

Dataset

  • PeMS03/04/07/08

These four datasets are available from Spatial-Temporal Synchronous Graph Convolutional Networks: A New Framework for Spatial-Temporal Network Data Forecasting

  • NE-BJ

This dataset is available from Dynamic Graph Convolutional Recurrent Network for Traffic Prediction: Benchmark and Solution

The default data path is ../../traffic/XXX as by data.py.

Environment

We use minimal environment requirement as below. Our code is tested on CUDA 11.1

numpy
pandas
torch==1.9.0

Run

cd SimpleSTG
python run.py

More configurations other than default can be found in run.py.

About

Code for "Understanding and Simplifying Architecture Search in Spatio-Temporal Graph Neural Networks" accepted by TMLR 2023

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages