search

DaehanKim / vgae_pytorch

This repository implements variational graph auto encoder by Thomas Kipf.
MIT License
385 stars 73 forks source link

About Node Classification #1

Closed Yfhu1103 closed 4 years ago

Yfhu1103 commented 4 years ago

Hello, Thanks for releasing your work! I have seen that you said you use GAE for node classification tasks but can not get good results, have you found why? And could you plz release the code for node classification?

DaehanKim commented 4 years ago

Hi, @Mrslock. I didn't do further experiments on that. As Kipf mentioned on his repo issue board, I also suspect main causes are lack of regularization such as early stopping or negative sampling. I'm afraid I don't have the specific implementation but you can easily try those unsupervised node classification. I referred to the description of a paper, 'A graph autoencoder for attributed network embedding'.

Best regard, Daehan