8000 GitHub - sailfish009/epcb-gnns
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

sailfish009/epcb-gnns

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Breaking the Expressive Bottlenecks of Graph Neural Networks

The code is built upon the PyTorch Geometric.

Prerequisites

python 3.6.9

pytorch 1.5.1

pytorch-geometric 1.5.0

ogb 1.2.1

Additional modules: numpy, easydict, tensorboardx

Running the tests

Running the ogbg-ppa test.

  • cd ogbg/ppa
  • Set hyper-parameters in ogbg-ppa.json.
  • Set CUDA_VISIBLE_DEVICES and output directory in run_script.sh.
  • chmod +x run_script.sh
  • ./run_script.sh

Running the ogbg-code test.

  • cd ogbg/code
  • Set hyper-parameters in ogbg-code.json.
  • Set CUDA_VISIBLE_DEVICES and output directory in run_script.sh.
  • chmod +x run_script.sh
  • ./run_script.sh

Running the ogbg-molhiv test.

  • cd ogbg/mol
  • Set hyper-parameters in ogbg-mol.json.
  • Set CUDA_VISIBLE_DEVICES and output directory in run_script.sh.
  • chmod +x run_script.sh
  • ./run_script.sh

Running the QM9 test.

  • cd ogbg/qm9
  • Set hyper-parameters in QM9.json.
  • Set CUDA_VISIBLE_DEVICES and output directory in run_script.sh.
  • chmod +x run_script.sh
  • ./run_script.sh

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

< 303D span data-view-component="true" class="Progress">
  • Python 97.4%
  • Shell 2.6%
0