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)

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)	Adds a child module to the current module.
apply(fn)	Applies 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])	Returns an iterator over module buffers.
children()	Returns an iterator over immediate children modules.
cpu()	Moves all model parameters and buffers to the CPU.
cuda([device])	Moves all model parameters and buffers to the GPU.
double()	Casts all floating point parameters and buffers to double datatype.
eval()	Sets the module in evaluation mode.
extra_repr()	Set 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)	Returns the buffer given by target if it exists, otherwise throws an error.
get_extra_state()	Returns any extra state to include in the module's state_dict.
get_parameter(target)	Returns the parameter given by target if it exists, otherwise throws an error.
get_submodule(target)	Returns the submodule given by target if it exists, otherwise throws an error.
half()	Casts all floating point parameters and buffers to half datatype.
ipu([device])	Moves all model parameters and buffers to the IPU.
load_state_dict(state_dict[, strict])	Copies parameters and buffers from state_dict into this module and its descendants.
modules()	Returns an iterator over all modules in the network.
named_buffers([prefix, recurse, ...])	Returns an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
named_children()	Returns 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])	Returns 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, ...])	Returns an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
parameters([recurse])	Returns an iterator over module parameters.
register_backward_hook(hook)	Registers a backward hook on the module.
register_buffer(name, tensor[, persistent])	Adds a buffer to the module.
register_forward_hook(hook, *[, prepend, ...])	Registers a forward hook on the module.
register_forward_pre_hook(hook, *[, ...])	Registers a forward pre-hook on the module.
register_full_backward_hook(hook[, prepend])	Registers a backward hook on the module.
register_full_backward_pre_hook(hook[, prepend])	Registers a backward pre-hook on the module.
register_load_state_dict_post_hook(hook)	Registers a post hook to be run after module's load_state_dict is called.
register_module(name, module)	Alias for add_module().
register_parameter(name, param)	Adds a parameter to the module.
register_state_dict_pre_hook(hook)	These hooks will be called with arguments: self, prefix, and keep_vars before calling state_dict on self.
requires_grad_([requires_grad])	Change if autograd should record operations on parameters in this module.
set_extra_state(state)	This function is called from load_state_dict() to handle any extra state found within the state_dict.
share_memory()	See torch.Tensor.share_memory_()
state_dict(*args[, destination, prefix, ...])	Returns a dictionary containing references to the whole state of the module.
to(*args, **kwargs)	Moves and/or casts the parameters and buffers.
to_empty(*, device)	Moves the parameters and buffers to the specified device without copying storage.
train([mode])	Sets the module in training mode.
type(dst_type)	Casts all parameters and buffers to dst_type.
xpu([device])	Moves all model parameters and buffers to the XPU.
zero_grad([set_to_none])	Sets gradients of all model parameters to zero.

__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)

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.