search

GentleZhu / EGI

Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization (NeurIPS 21')
23 stars 5 forks source link

The code does not support transfer learning across graphs currently #2

Open PonderLY opened 2 years ago

PonderLY commented 2 years ago

Hi GentleZhu,

I found that the code does not handle the scenario when data-id and data-src are different. I am not sure whether I miss any key part in the code.

Thanks and Regards, PonderLY

Skyorca commented 1 year ago

EGI is a two-stage model, thus you can dump the best embedding model and the best classifier seperately while training on source graph, then you can load target graph and apply the dumpled models to it :)