Inductive or transductive DistDGL GraphSAGE?

Questions
,
#1

Just want to confirm something:

The distributed GraphSAGE code in graphsage/experimental is doing inductive learning, correct? (i.e. during training only the training nodes are seen)

Thank you.

#2

It’s transductive. All nodes’ features are known in the training process, but only training nodes have labels

#3

Thanks for the info!

#4

The GraphSage model for distributed training is inductive.

#5

Does this mean that the single host GraphSAGE (and GCN, if I may ask as well) are transductive while the distributed one is inductive?

#6

The single-machine version of GraphSAGE allows both transductive learning and inductive learning. GCN was originally developed for transductive learning but can be used for inductive learning as well.