About semi-supervised learning
junkangwu opened this issue · comments
junkang Wu commented
Hi, here!
Recently, I'm confused about semi-supervised classification in GCN.
-
In other words, how the lose function (1)
$\lambda \times L_{reg}$
is implemented? I can't find it in the code. May I ask you about its implementation? -
As it's mentioned in the paper, semi-supervised is focused on some datas which are unlabeled.But all data in
cora, pubmed and citeseer
are labeled. so it is depend on thesample_mask
? Or they are masked while training? Could you explain it for me in detailed or give an simple example?
Thanks a lot ! Looking forward to your help!