search

twjiang / graphSAGE-pytorch

A PyTorch implementation of GraphSAGE. This package contains a PyTorch implementation of GraphSAGE.
621 stars 150 forks source link

typo in line 73 of main.py? #16

Closed jaks19 closed 3 years ago

jaks19 commented 3 years ago

Do you want to check =='unsup' to allow classification training as it is now?

Or should it rather be !='unsup'?

It does not make sense to me that when we specify 'unsup' that classification is still used for training. But I may be missing something?

Thanks

zhao-tong commented 3 years ago

No, it's not a typo. The classification model is independent from the main model. We need to train a classification MLP to evaluate the representations.

jaks19 commented 3 years ago

No, it's not a typo. The classification model is independent from the main model. We need to train a classification MLP to evaluate the representations.

That makes a lot of sense, thanks for the clarification!