models.nn.gat

Module Contents

Classes

GraphAttentionLayer	Simple GAT layer, similar to https://arxiv.org/abs/1710.10903
SpecialSpmmFunction	Special function for only sparse region backpropataion layer.
SpecialSpmm
SpGraphAttentionLayer	Sparse version GAT layer, similar to https://arxiv.org/abs/1710.10903
PetarVGAT
PetarVSpGAT

class models.nn.gat.GraphAttentionLayer(in_features, out_features, dropout, alpha, concat=True)

Bases: torch.nn.Module

Simple GAT layer, similar to https://arxiv.org/abs/1710.10903

forward(self, input, adj)

__repr__(self)

class models.nn.gat.SpecialSpmmFunction

Bases: torch.autograd.Function

Special function for only sparse region backpropataion layer.

static forward(ctx, indices, values, shape, b)

static backward(ctx, grad_output)

class models.nn.gat.SpecialSpmm

Bases: torch.nn.Module

forward(self, indices, values, shape, b)

class models.nn.gat.SpGraphAttentionLayer(in_features, out_features, dropout, alpha, concat=True)

Bases: torch.nn.Module

Sparse version GAT layer, similar to https://arxiv.org/abs/1710.10903

forward(self, input, edge)

__repr__(self)

class models.nn.gat.PetarVGAT(nfeat, nhid, nclass, dropout, alpha, nheads)

Bases: 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.

forward(self, x, adj)

class models.nn.gat.PetarVSpGAT(nfeat, nhid, nclass, dropout, alpha, nheads)

Bases: models.nn.gat.PetarVGAT

forward(self, x, adj)

loss(self, data)

predict(self, data)