We do not need to split the dataset into batches?

[BierOne]

Hi, chengsen.

I noticed that you directly train the model using the whole corpus, and you even do not split the corpus into batches. I am confused about this. Is this the way that the paper authors applied?

Besides, if so, how can we build the connection between the input document and the target label. I cannot find any clues if we train the model in this way.

Look forward to your reply. Thx.

regards, bill

[cdqncn]

GCN就是full batch方式