Question about the classifiers

[AnonymousGeeek]

I have some questions about the use of classifiers:

The classifiers you used to train the neighbor generator in models.py is:
self.classifier=GNN(nfeat=feat_shape, nhid=config.hidden, nclass=n_classes, dropout=config.dropout)
But the classifier you used in classifiers.py for the task is:
graphsage_model=GraphSAGE(layer_sizes=config.classifier_layer_sizes, generator=fillG_node_gen, n_samples=config.num_samples)

I would like to know why not use the same classifier (eg. GraphSAGE) instead of using the expanded graph to train a new classifier?