Skip to content

Implementation of the Variational Graph Auto-encoder in Spektral (Tensorflow-Keras)

License

Notifications You must be signed in to change notification settings

FilippoMB/Variational-Graph-Auto-encoders-Tensorflow-2-Spektral-

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Variational Graph Auto-encoders in Spektral

This is a re-implementation of the Graph Auto-encoder and Variational Graph Auto-encoder presented here.

This implementation is based on Spektral, the Tensorflow-Keras library for Graph Neural Networks. Compared to the original implementation, the code is more compact and the scripts are self-contained.

The results obtained are slightly different from those reported in the original paper (the AUC is actually higher here). Also, the results show that there is not a significant improvement in using the variational variant compared to the deterministic one.

About

Implementation of the Variational Graph Auto-encoder in Spektral (Tensorflow-Keras)

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages