Skip to content

Vanilla Implementation of Graph Convolutional Networks

License

Notifications You must be signed in to change notification settings

cshjin/GCN-TF2.0

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

49 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

GCN-TF2.0

This is the vanilla implementation of graph convolution networks (GCN) with tensorflow 2.x.

Instead of the Keras API, this implementation take the GradientTape as the optimization process.

No placeholder, no tf.app, tf.flags, and some APIs deprecated after TF 2.x.

Reference: Semi-Supervised Classification with Graph Convolutional Networks.

Parts of the code coming from the author's original implementation code.

Credits to Thomas Kipf. Thanks.

usage

python train.py [options]

You can specify the options as

  --dataset, choosing from 'citeseer', 'cora', 'cora_ml', 'pubmed', 'polblogs' and 'dblp'

Check out the train.py for more detailed arguments.

LICENSE

The project is under MIT license.

About

Vanilla Implementation of Graph Convolutional Networks

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages