I am struggling to understand the training part of the paper Semi-Supervised Classification with Graph Convolutional Networks (2017) by Thomas Kipf and Max Welling. The GitHub repo is here.
I do not understand how masking should be performed. I input the whole data, but I use a small portion of labeled data to train.
Here, should I mask the rest of the data? What will be my test set then? Can someone who has worked on this before please guide me through?