Backbones#

Convolutional Cell Convolutional Network (CCCN) model.

class topobenchmarkx.nn.backbones.cell.cccn.CCCN(in_channels, n_layers=2, dropout=0.0, last_act=False)[source]#

CCCN model.

Parameters:

in_channelsint: Number of input channels.
n_layersint, optional: Number of layers (default: 2).
dropoutfloat, optional: Dropout rate (default: 0).
last_actbool, optional: If True, the last activation function is applied (default: False).

forward(x, Ld, Lu)[source]#

Forward pass.

Parameters:

xtorch.Tensor: Input tensor.
Ldtorch.Tensor: Domain adjacency matrix.
Lutorch.Tensor: Label adjacency matrix.

Returns:

torch.Tensor: Output tensor.

class topobenchmarkx.nn.backbones.cell.cccn.CW(F_in, F_out)[source]#

Layer of the CCCN model.

Parameters:

F_inint: Number of input channels.
F_outint: Number of output channels.

forward(xe, Lu, Ld)[source]#

Forward pass.

Parameters:

xetorch.Tensor: Input tensor.
Lutorch.Tensor: Domain adjacency matrix.
Ldtorch.Tensor: Label adjacency matrix.

Returns:

torch.Tensor: Output tensor.

Class implementing the EDGNN model.

class topobenchmarkx.nn.backbones.hypergraph.edgnn.EDGNN(num_features, input_dropout=0.2, dropout=0.2, activation='relu', MLP_num_layers=2, MLP2_num_layers=-1, MLP3_num_layers=-1, All_num_layers=2, edconv_type='EquivSet', restart_alpha=0.5, aggregate='add', normalization='None', AllSet_input_norm=False)[source]#

EDGNN model.

Parameters:

num_featuresint: Number of input features.
input_dropoutfloat, optional: Dropout rate for input features. Defaults to 0.2.
dropoutfloat, optional: Dropout rate for hidden layers. Defaults to 0.2.
activationstr, optional: Activation function. Defaults to ‘relu’.
MLP_num_layersint, optional: Number of layers in MLP. Defaults to 2.
MLP2_num_layersint, optional: Number of layers in the second MLP. Defaults to -1.
MLP3_num_layersint, optional: Number of layers in the third MLP. Defaults to -1.
All_num_layersint, optional: Number of layers in the EDConv. Defaults to 2.
edconv_typestr, optional: Type of EDConv. Defaults to ‘EquivSet’.
restart_alphafloat, optional: Restart alpha. Defaults to 0.5.
aggregatestr, optional: Aggregation method. Defaults to ‘add’.
normalizationstr, optional: Normalization method. Defaults to ‘None’.
AllSet_input_normbool, optional: Whether to normalize input features. Defaults to False.

forward(x, edge_index)[source]#

Forward pass.

Parameters:

xTensor: Input features.
edge_indexLongTensor: Edge index.

Returns:

Tensor: Output features.
None: None object needed for compatibility.

reset_parameters()[source]#: Reset parameters.

class topobenchmarkx.nn.backbones.hypergraph.edgnn.EquivSetConv(in_features, out_features, mlp1_layers=1, mlp2_layers=1, mlp3_layers=1, aggr='add', alpha=0.5, dropout=0.0, normalization='None', input_norm=False)[source]#

Class implementing the Equivariant Set Convolution.

Parameters:

in_featuresint: Number of input features.
out_featuresint: Number of output features.
mlp1_layersint, optional: Number of layers in the first MLP. Defaults to 1.
mlp2_layersint, optional: Number of layers in the second MLP. Defaults to 1.
mlp3_layersint, optional: Number of layers in the third MLP. Defaults to 1.
aggrstr, optional: Aggregation method. Defaults to ‘add’.
alphafloat, optional: Alpha value. Defaults to 0.5.
dropoutfloat, optional: Dropout rate. Defaults to 0.0.
normalizationstr, optional: Normalization method. Defaults to ‘None’.
input_normbool, optional: Whether to normalize input features. Defaults to False.

forward(X, vertex, edges, X0)[source]#

Forward pass.

Parameters:

XTensor: Input features.
vertexLongTensor: Vertex index.
edgesLongTensor: Edge index.
X0Tensor: Initial features.

Returns:

Tensor: Output features.

reset_parameters()[source]#: Reset parameters.

class topobenchmarkx.nn.backbones.hypergraph.edgnn.JumpLinkConv(in_features, out_features, mlp_layers=2, aggr='add', alpha=0.5)[source]#

Class implementing the JumpLink Convolution.

Parameters:

in_featuresint: Number of input features.
out_featuresint: Number of output features.
mlp_layersint, optional: Number of layers in the MLP. Defaults to 2.
aggrstr, optional: Aggregation method. Defaults to ‘add’.
alphafloat, optional: Alpha value. Defaults to 0.5.

forward(X, vertex, edges, X0, beta=1.0)[source]#

Forward pass.

Parameters:

XTensor: Input features.
vertexLongTensor: Vertex index.
edgesLongTensor: Edge index.
X0Tensor: Initial features.
betafloat, optional: Beta value. Defaults to 1.0.

Returns:

Tensor: Output features.

reset_parameters()[source]#: Reset parameters.

class topobenchmarkx.nn.backbones.hypergraph.edgnn.MLP(in_channels, hidden_channels, out_channels, num_layers, dropout=0.5, Normalization='bn', InputNorm=False)[source]#

Class implementing a multi-layer perceptron.

Adapted from CUAI/CorrectAndSmooth

Parameters:

in_channelsint: Number of input features.
hidden_channelsint: Number of hidden features.
out_channelsint: Number of output features.
num_layersint: Number of layers.
dropoutfloat, optional: Dropout rate. Defaults to 0.5.
Normalizationstr, optiona: Normalization method. Defaults to ‘bn’.
InputNormbool, optional: Whether to normalize input features. Defaults to False.

flops(x)[source]#

Calculate FLOPs.

Parameters:

xTensor: Input features.

Returns:

int: FLOPs.

forward(x)[source]#

Forward pass.

Parameters:

xTensor: Input features.

Returns:

Tensor: Output features.

reset_parameters()[source]#: Reset parameters.

class topobenchmarkx.nn.backbones.hypergraph.edgnn.MeanDegConv(in_features, out_features, init_features=None, mlp1_layers=1, mlp2_layers=1, mlp3_layers=2)[source]#

Class implementing the Mean Degree Convolution.

Parameters:

in_featuresint: Number of input features.
out_featuresint: Number of output features.
init_featuresint, optional: Number of initial features. Defaults to None.
mlp1_layersint, optional: Number of layers in the first MLP. Defaults to 1.
mlp2_layersint, optional: Number of layers in the second MLP. Defaults to 1.
mlp3_layersint, optional: Number of layers in the third MLP. Defaults to 2.

forward(X, vertex, edges, X0)[source]#

Forward pass.

Parameters:

XTensor: Input features.
vertexLongTensor: Vertex index.
edgesLongTensor: Edge index.
X0Tensor: Initial features.

Returns:

Tensor: Output features.

reset_parameters()[source]#: Reset parameters.

class topobenchmarkx.nn.backbones.hypergraph.edgnn.PlainMLP(in_channels, hidden_channels, out_channels, num_layers, dropout=0.5)[source]#

Class implementing a multi-layer perceptron without normalization.

Adapted from CUAI/CorrectAndSmooth.

Parameters:

in_channelsint: Number of input features.
hidden_channelsint: Number of hidden features.
out_channelsint: Number of output features.
num_layersint: Number of layers.
dropoutfloat, optional: Dropout rate. Defaults to 0.5.

forward(x)[source]#

Forward pass.

Parameters:

xTensor: Input features.

Returns:

Tensor: Output features.

reset_parameters()[source]#: Reset parameters.

Implementation of the Simplicial Complex Convolutional Neural Network (SCCNN) for complex classification.

class topobenchmarkx.nn.backbones.simplicial.sccnn.SCCNNCustom(in_channels_all, hidden_channels_all, conv_order, sc_order, aggr_norm=False, update_func=None, n_layers=2)[source]#

SCCNN implementation for complex classification.

Note: In this task, we can consider the output on any order of simplices for the classification task, which of course can be amended by a readout layer.

Parameters:

in_channels_alltuple of int: Dimension of input features on (nodes, edges, faces).
hidden_channels_alltuple of int: Dimension of features of hidden layers on (nodes, edges, faces).
conv_orderint: Order of convolutions, we consider the same order for all convolutions.
sc_orderint: Order of simplicial complex.
aggr_normbool, optional: Whether to normalize the aggregation (default: False).
update_funcstr, optional: Update function for the simplicial complex convolution (default: None).
n_layersint, optional: Number of layers (default: 2).

forward(x_all, laplacian_all, incidence_all)[source]#

Forward computation.

Parameters:

x_alltuple(tensors): Tuple of feature tensors (node, edge, face).
laplacian_alltuple(tensors): Tuple of Laplacian tensors (graph laplacian L0, down edge laplacian L1_d, upper edge laplacian L1_u, face laplacian L2).
incidence_alltuple(tensors): Tuple of order 1 and 2 incidence matrices.

Returns:

tuple(tensors): Tuple of final hidden state tensors (node, edge, face).

class topobenchmarkx.nn.backbones.simplicial.sccnn.SCCNNLayer(in_channels, out_channels, conv_order, sc_order, aggr_norm: bool = False, update_func=None, initialization: str = 'xavier_normal')[source]#

Layer of a Simplicial Complex Convolutional Neural Network.

Parameters:

in_channelstuple of int: Dimensions of input features on nodes, edges, and faces.
out_channelstuple of int: Dimensions of output features on nodes, edges, and faces.
conv_orderint: Convolution order of the simplicial filters.
sc_orderint: SC order.
aggr_normbool, optional: Whether to normalize the aggregated message by the neighborhood size (default: False).
update_funcstr, optional: Activation function used in aggregation layers (default: None).
initializationstr, optional: Initialization method for the weights (default: “xavier_normal”).

aggr_norm_func(conv_operator, x)[source]#

Perform aggregation normalization.

Parameters:

conv_operatortorch.sparse: Convolution operator.
xtorch.Tensor: Feature tensor.

Returns:

torch.Tensor: Normalized feature tensor.

chebyshev_conv(conv_operator, conv_order, x)[source]#

Perform Chebyshev convolution.

Parameters:

conv_operatortorch.sparse: Convolution operator.
conv_orderint: Order of the convolution.
xtorch.Tensor: Feature tensor.

Returns:

torch.Tensor: Output tensor.

forward(x_all, laplacian_all, incidence_all)[source]#

Forward computation.

Parameters:

x_alltuple of tensors: Tuple of input feature tensors (node, edge, face).
laplacian_alltuple of tensors: Tuple of Laplacian tensors (graph laplacian L0, down edge laplacian L1_d, upper edge laplacian L1_u, face laplacian L2).
incidence_alltuple of tensors: Tuple of order 1 and 2 incidence matrices.

Returns:

torch.Tensor: Output tensor for each 0-cell.
torch.Tensor: Output tensor for each 1-cell.
torch.Tensor: Output tensor for each 2-cell.

reset_parameters(gain: float = 1.414)[source]#

Reset learnable parameters.

Parameters:

gainfloat: Gain for the weight initialization.

update(x)[source]#

Update embeddings on each cell (step 4).

Parameters:

xtorch.Tensor: Input tensor.

Returns:

torch.Tensor: Updated tensor.