DaehanKim / vgae_pytorch

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

more graphs train #10

Closed secuy closed 11 months ago

secuy commented 11 months ago

Hello, now if I have many graphs, how can train these data? It seems that the code can just train on one graph data.

DaehanKim commented 11 months ago

Hi @secuy This implementation is based on GCN architecture, which only supports link prediction within a single graph. I strongly recommend you to check out other inductive frameworks such as GraphSAGE, which can predict node representations from unseen graphs.

secuy commented 11 months ago

Okay, thanks for your answer and suggestion