search

vuptran / graph-representation-learning

Autoencoders for Link Prediction and Semi-Supervised Node Classification (DSAA 2018)
MIT License
252 stars 67 forks source link

Validation set generated but never used #6

Open saedr opened 4 years ago

saedr commented 4 years ago

Dear Phi, In the following piece of code you generate the validation set but never return it, instead you use the test set instead of validation set and there is no actual test set to be used for testing purposes.

https://github.com/vuptran/graph-representation-learning/blob/48d59781b1b66a3a639153a4eac5269cfd9b723c/longae/utils_gcn.py#L153-L172

Am I missing something?

vuptran commented 4 years ago

@saedr sorry for the really late response. You are correct, I don't use the val set, but subsume it into the training set. The test set (see below) is used for testing purposes.

https://github.com/vuptran/graph-representation-learning/blob/master/longae/utils_gcn.py#L183