CAN#

CAN class.

class topomodelx.nn.cell.can.CAN(in_channels_0, in_channels_1, out_channels, dropout=0.5, heads=2, concat=True, skip_connection=True, att_activation=None, n_layers=2, att_lift=True, pooling=False, k_pool=0.5, **kwargs)[source]#

CAN (Cell Attention Network) [1] module for graph classification.

Parameters:
in_channels_0int

Number of input channels for the node-level input.

in_channels_1int

Number of input channels for the edge-level input.

out_channelsint

Number of output channels.

dropoutfloat, optional

Dropout probability. Default is 0.5.

headsint, optional

Number of attention heads. Default is 2.

concatbool, optional

Whether to concatenate the output channels of attention heads. Default is True.

skip_connectionbool, optional

Whether to use skip connections. Default is True.

att_activationtorch.nn.Module, optional

Activation function for attention mechanism. Default is torch.nn.LeakyReLU(0.2).

n_layersint, default=2

Number of CAN layers.

att_liftbool, default=True

Whether to apply a lift the signal from node-level to edge-level input.

poolingbool, default=False

Whether to apply pooling operation.

k_poolfloat, default=0.5

The pooling ratio i.e, the fraction of r-cells to keep after the pooling operation.

**kwargsoptional

Additional arguments CANLayer.

Methods

add_module(name, module)

Add a child module to the current module.

apply(fn)

Apply fn recursively to every submodule (as returned by .children()) as well as self.

bfloat16()

Casts all floating point parameters and buffers to bfloat16 datatype.

buffers([recurse])

Return an iterator over module buffers.

children()

Return an iterator over immediate children modules.

compile(*args, **kwargs)

Compile this Module's forward using torch.compile().

cpu()

Move all model parameters and buffers to the CPU.

cuda([device])

Move all model parameters and buffers to the GPU.

double()

Casts all floating point parameters and buffers to double datatype.

eval()

Set the module in evaluation mode.

extra_repr()

Return the extra representation of the module.

float()

Casts all floating point parameters and buffers to float datatype.

forward(x_0, x_1, adjacency_0, ...)

Forward pass.

get_buffer(target)

Return the buffer given by target if it exists, otherwise throw an error.

get_extra_state()

Return any extra state to include in the module's state_dict.

get_parameter(target)

Return the parameter given by target if it exists, otherwise throw an error.

get_submodule(target)

Return the submodule given by target if it exists, otherwise throw an error.

half()

Casts all floating point parameters and buffers to half datatype.

ipu([device])

Move all model parameters and buffers to the IPU.

load_state_dict(state_dict[, strict, assign])

Copy parameters and buffers from state_dict into this module and its descendants.

modules([remove_duplicate])

Return an iterator over all modules in the network.

mtia([device])

Move all model parameters and buffers to the MTIA.

named_buffers([prefix, recurse, ...])

Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.

named_children()

Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.

named_modules([memo, prefix, remove_duplicate])

Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.

named_parameters([prefix, recurse, ...])

Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.

parameters([recurse])

Return an iterator over module parameters.

register_backward_hook(hook)

Register a backward hook on the module.

register_buffer(name, tensor[, persistent])

Add a buffer to the module.

register_forward_hook(hook, *[, prepend, ...])

Register a forward hook on the module.

register_forward_pre_hook(hook, *[, ...])

Register a forward pre-hook on the module.

register_full_backward_hook(hook[, prepend])

Register a backward hook on the module.

register_full_backward_pre_hook(hook[, prepend])

Register a backward pre-hook on the module.

register_load_state_dict_post_hook(hook)

Register a post-hook to be run after module's load_state_dict() is called.

register_load_state_dict_pre_hook(hook)

Register a pre-hook to be run before module's load_state_dict() is called.

register_module(name, module)

Alias for add_module().

register_parameter(name, param)

Add a parameter to the module.

register_state_dict_post_hook(hook)

Register a post-hook for the state_dict() method.

register_state_dict_pre_hook(hook)

Register a pre-hook for the state_dict() method.

requires_grad_([requires_grad])

Change if autograd should record operations on parameters in this module.

set_extra_state(state)

Set extra state contained in the loaded state_dict.

set_submodule(target, module[, strict])

Set the submodule given by target if it exists, otherwise throw an error.

share_memory()

See torch.Tensor.share_memory_().

state_dict(*args[, destination, prefix, ...])

Return a dictionary containing references to the whole state of the module.

to(*args, **kwargs)

Move and/or cast the parameters and buffers.

to_empty(*, device[, recurse])

Move the parameters and buffers to the specified device without copying storage.

train([mode])

Set the module in training mode.

type(dst_type)

Casts all parameters and buffers to dst_type.

xpu([device])

Move all model parameters and buffers to the XPU.

zero_grad([set_to_none])

Reset gradients of all model parameters.

__call__

References

[1]

Giusti, Battiloro, Testa, Di Lorenzo, Sardellitti and Barbarossa. Cell attention networks (2022). Paper: https://arxiv.org/pdf/2209.08179.pdf Repository: lrnzgiusti/can

forward(x_0, x_1, adjacency_0, down_laplacian_1, up_laplacian_1)[source]#

Forward pass.

Parameters:
x_0torch.Tensor, shape = (n_nodes, in_channels_0)

Input features on the nodes (0-cells).

x_1torch.Tensor, shape = (n_edges, in_channels_1)

Input features on the edges (1-cells).

adjacency_0torch.Tensor, shape = (n_nodes, n_nodes)

Neighborhood matrix from nodes to nodes.

down_laplacian_1torch.Tensor, shape = (-, -)

Lower Neighbourhood matrix.

up_laplacian_1torch.Tensor, shape = (-, -)

Upper neighbourhood matrix.

Returns:
torch.Tensor, shape = (num_pooled_edges, heads * out_channels)

Final hidden representations of pooled edges.