topobench.nn.backbones.graph package#

Submodules#

topobench.nn.backbones.graph.graph_mlp module#

Graph MLP backbone from yanghu819/Graph-MLP.

class topobench.nn.backbones.graph.graph_mlp.GraphMLP(in_channels, hidden_channels, order=1, dropout=0.0, **kwargs)[source]#

Bases: Module

“Graph MLP backbone.

Parameters:

in_channelsint: Number of input features.
hidden_channelsint: Number of hidden units.
orderint, optional: To compute order-th power of adj matrix (default: 1).
dropoutfloat, optional: Dropout rate (default: 0.0).
**kwargs: Additional arguments.

forward(x)[source]#

Forward pass.

Parameters:

xtorch.Tensor: Input tensor.

Returns:

torch.Tensor: Output tensor.

class topobench.nn.backbones.graph.graph_mlp.Mlp(input_dim, hid_dim, dropout)[source]#

Bases: Module

MLP module.

Parameters:

input_dimint: Input dimension.
hid_dimint: Hidden dimension.
dropoutfloat: Dropout rate.

forward(x)[source]#

Forward pass.

Parameters:

xtorch.Tensor: Input tensor.

Returns:

torch.Tensor: Output tensor.

topobench.nn.backbones.graph.graph_mlp.get_feature_dis(x)[source]#

Get feature distance matrix.

Parameters:

xtorch.Tensor: Input tensor.

Returns:

torch.Tensor: Feature distance matrix.

topobench.nn.backbones.graph.identity_gnn module#

This module contains the implementation of identity GNNs.

class topobench.nn.backbones.graph.identity_gnn.IdentityGAT(in_channels, hidden_channels, out_channels, num_layers, norm, heads=1, dropout=0.0)[source]#

Bases: Module

Graph Attention Network (GAT) with identity activation function.

Parameters:

in_channelsint: Number of input features.
hidden_channelsint: Number of hidden units.
out_channelsint: Number of output features.
num_layersint: Number of layers.
normtorch.nn.Module: Normalization layer.
headsint, optional: Number of attention heads. Defaults to 1.
dropoutfloat, optional: Dropout rate. Defaults to 0.0.

forward(x, edge_index)[source]#

Forward pass.

Parameters:

xtorch.Tensor: Input node features.
edge_indextorch.Tensor: Edge indices.

Returns:

torch.Tensor: Output node features.

class topobench.nn.backbones.graph.identity_gnn.IdentityGCN(in_channels, hidden_channels, out_channels, num_layers, norm, dropout=0.0)[source]#

Bases: Module

Graph Convolutional Network (GCN) with identity activation function.

Parameters:

in_channelsint: Number of input features.
hidden_channelsint: Number of hidden units.
out_channelsint: Number of output features.
num_layersint: Number of layers.
normtorch.nn.Module: Normalization layer.
dropoutfloat, optional: Dropout rate. Defaults to 0.0.

forward(x, edge_index)[source]#

Forward pass.

Parameters:

xtorch.Tensor: Input node features.
edge_indextorch.Tensor: Edge indices.

Returns:

torch.Tensor: Output node features.

class topobench.nn.backbones.graph.identity_gnn.IdentityGIN(in_channels, hidden_channels, out_channels, num_layers, norm, dropout=0.0)[source]#

Bases: Module

Graph Isomorphism Network (GIN) with identity activation function.

Parameters:

in_channelsint: Number of input features.
hidden_channelsint: Number of hidden units.
out_channelsint: Number of output features.
num_layersint: Number of layers.
normtorch.nn.Module: Normalization layer.
dropoutfloat, optional: Dropout rate. Defaults to 0.0.

forward(x, edge_index)[source]#

Forward pass.

Parameters:

xtorch.Tensor: Input node features.
edge_indextorch.Tensor: Edge indices.

Returns:

torch.Tensor: Output node features.

class topobench.nn.backbones.graph.identity_gnn.IdentitySAGE(in_channels, hidden_channels, out_channels, num_layers, norm, dropout=0.0)[source]#

Bases: Module

GraphSAGE with identity activation function.

Parameters:

in_channelsint: Number of input features.
hidden_channelsint: Number of hidden units.
out_channelsint: Number of output features.
num_layersint: Number of layers.
normtorch.nn.Module: Normalization layer.
dropoutfloat, optional: Dropout rate. Defaults to 0.0.

forward(x, edge_index)[source]#

Forward pass.

Parameters:

xtorch.Tensor: Input node features.
edge_indextorch.Tensor: Edge indices.

Returns:

torch.Tensor: Output node features.

Module contents#

Graph backbones with automated exports.

class topobench.nn.backbones.graph.GraphMLP(in_channels, hidden_channels, order=1, dropout=0.0, **kwargs)#

Bases: Module

“Graph MLP backbone.

Parameters:

in_channelsint: Number of input features.
hidden_channelsint: Number of hidden units.
orderint, optional: To compute order-th power of adj matrix (default: 1).
dropoutfloat, optional: Dropout rate (default: 0.0).
**kwargs: Additional arguments.

forward(x)#

Forward pass.

Parameters:

xtorch.Tensor: Input tensor.

Returns:

torch.Tensor: Output tensor.

class topobench.nn.backbones.graph.IdentityGAT(in_channels, hidden_channels, out_channels, num_layers, norm, heads=1, dropout=0.0)#

Bases: Module

Graph Attention Network (GAT) with identity activation function.

Parameters:

in_channelsint: Number of input features.
hidden_channelsint: Number of hidden units.
out_channelsint: Number of output features.
num_layersint: Number of layers.
normtorch.nn.Module: Normalization layer.
headsint, optional: Number of attention heads. Defaults to 1.
dropoutfloat, optional: Dropout rate. Defaults to 0.0.

forward(x, edge_index)#

Forward pass.

Parameters:

xtorch.Tensor: Input node features.
edge_indextorch.Tensor: Edge indices.

Returns:

torch.Tensor: Output node features.

class topobench.nn.backbones.graph.IdentityGCN(in_channels, hidden_channels, out_channels, num_layers, norm, dropout=0.0)#

Bases: Module

Graph Convolutional Network (GCN) with identity activation function.

Parameters:

in_channelsint: Number of input features.
hidden_channelsint: Number of hidden units.
out_channelsint: Number of output features.
num_layersint: Number of layers.
normtorch.nn.Module: Normalization layer.
dropoutfloat, optional: Dropout rate. Defaults to 0.0.

forward(x, edge_index)#

Forward pass.

Parameters:

xtorch.Tensor: Input node features.
edge_indextorch.Tensor: Edge indices.

Returns:

torch.Tensor: Output node features.

class topobench.nn.backbones.graph.IdentityGIN(in_channels, hidden_channels, out_channels, num_layers, norm, dropout=0.0)#

Bases: Module

Graph Isomorphism Network (GIN) with identity activation function.

Parameters:

in_channelsint: Number of input features.
hidden_channelsint: Number of hidden units.
out_channelsint: Number of output features.
num_layersint: Number of layers.
normtorch.nn.Module: Normalization layer.
dropoutfloat, optional: Dropout rate. Defaults to 0.0.

forward(x, edge_index)#

Forward pass.

Parameters:

xtorch.Tensor: Input node features.
edge_indextorch.Tensor: Edge indices.

Returns:

torch.Tensor: Output node features.

class topobench.nn.backbones.graph.IdentitySAGE(in_channels, hidden_channels, out_channels, num_layers, norm, dropout=0.0)#

Bases: Module

GraphSAGE with identity activation function.

Parameters:

in_channelsint: Number of input features.
hidden_channelsint: Number of hidden units.
out_channelsint: Number of output features.
num_layersint: Number of layers.
normtorch.nn.Module: Normalization layer.
dropoutfloat, optional: Dropout rate. Defaults to 0.0.

forward(x, edge_index)#

Forward pass.

Parameters:

xtorch.Tensor: Input node features.
edge_indextorch.Tensor: Edge indices.

Returns:

torch.Tensor: Output node features.

class topobench.nn.backbones.graph.Mlp(input_dim, hid_dim, dropout)#

Bases: Module

MLP module.

Parameters:

input_dimint: Input dimension.
hid_dimint: Hidden dimension.
dropoutfloat: Dropout rate.

forward(x)#

Forward pass.

Parameters:

xtorch.Tensor: Input tensor.

Returns:

torch.Tensor: Output tensor.

topobench.nn.backbones.graph package#

Submodules#

topobench.nn.backbones.graph.graph_mlp module#

topobench.nn.backbones.graph.identity_gnn module#

Module contents#

This Page