models.nn.pyg_han

Module Contents

Classes

AttentionLayer

HANLayer

HAN

class models.nn.pyg_han.AttentionLayer(num_features)[source]

Bases: torch.nn.Module

forward(self, x)[source]
class models.nn.pyg_han.HANLayer(num_edge, w_in, w_out)[source]

Bases: torch.nn.Module

forward(self, x, adj)[source]
class models.nn.pyg_han.HAN(num_edge, w_in, w_out, num_class, num_nodes, num_layers)[source]

Bases: models.BaseModel

static add_args(parser)[source]

Add model-specific arguments to the parser.

classmethod build_model_from_args(cls, args)[source]

Build a new model instance.

forward(self, A, X, target_x, target)[source]
loss(self, data)[source]
evaluate(self, data, nodes, targets)[source]