gammagl.models.GraphSAGE_Sample_Model

class GraphSAGE_Sample_Model(in_feat, hid_feat, out_feat, drop_rate, num_layers, name=None)

The GraphSAGE operator from the “Inductive Representation Learning on Large Graphs” paper

Parameters:

• in_feat – number of input feature.

• hid_feat – number of hidden feature.

• out_feat – number of output feature.

• drop_rate – dropout rate.

• num_layers – number of sage layers.

• name – model name.

forward(x, edgeIndices)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

inference(feat, dataloader, cur_x)