GraphClassification&BatchwiseTraining

Hi I have two questions:

• I would like to repurpose this for graph classification (where I have a single label per graph). I see there is an option to choose
  

  1	featureless&＃061;False

  when defining a new

  1	GraphConvolution

  layer. However, the loss is still computed for each node, and I was wondering how I should change your code.



• In the context of graph classification, how should I modify your
  

  1

  train.py

  for batch-wise training?

Thanks for putting this together!

该提问来源于开源项目：tkipf/gcn