cogdl.models.nn.asgcn

Module Contents

Classes

GraphConvolution	Simple GCN layer, similar to https://arxiv.org/abs/1609.02907
ASGCN

class cogdl.models.nn.asgcn.GraphConvolution(in_features, out_features, bias=True)

Bases: torch.nn.Module

Simple GCN layer, similar to https://arxiv.org/abs/1609.02907

reset_parameters(self)

forward(self, input, adj)

__repr__(self)

class cogdl.models.nn.asgcn.ASGCN(num_features, num_classes, hidden_size, num_layers, dropout, sample_size)

Bases: cogdl.models.BaseModel

static add_args(parser)

Add model-specific arguments to the parser.

classmethod build_model_from_args(cls, args)

Build a new model instance.

reset_parameters(self)

set_adj(self, edge_index, num_nodes)

compute_adjlist(self, sp_adj, max_degree=32)

Transfer sparse adjacent matrix to adj-list format

from_adjlist(self, adj)

Transfer adj-list format to sparsetensor

_sample_one_layer(self, x, adj, v, sample_size)

sampling(self, x, v)

forward(self, x, adj)