Garfield.nn.GATDecoder

class Garfield.nn.GATDecoder(in_channels, hidden_dims, out_channels, conv_type, num_heads, dropout, concat, num_domains='', used_edge_weight=False, used_DSBN=False)

Graph Attention Network (GAT) Decoder class.

This class implements a GAT-based decoder for reconstructing node features from latent representations. It supports domain-specific batch normalization (DSBN) and edge weights.

Parameters:

• in_channels (int) – Number of input feature dimensions.

• hidden_dims (list[int]) – List of output dimensions for each hidden GAT layer, in ascending order.

• out_channels (int) – Number of output feature dimensions.

• conv_type (str) – Type of GAT convolution layer to use (‘GAT’ or ‘GATv2Conv’).

• num_heads (int) – Number of attention heads for each GAT layer.

• dropout (float) – Dropout rate applied to GAT layers.

• concat (bool) – Whether to concatenate the output of all attention heads or not.

• num_domains (int or str) – Number of domains for domain-specific batch normalization (DSBN). If 1, regular batch normalization is used.

• used_edge_weight (bool, optional) – Whether to use edge weights in the GAT layers. Default is False.

• used_DSBN (bool, optional) – Whether to use domain-specific batch normalization (DSBN). Default is False.

__init__(in_channels, hidden_dims, out_channels, conv_type, num_heads, dropout, concat, num_domains='', used_edge_weight=False, used_DSBN=False)

Initializes the GATDecoder, which consists of multiple Graph Attention Network (GAT) layers followed by domain-specific normalization (if applicable).

Methods

__init__(in_channels, hidden_dims, ...[, ...])	Initializes the GATDecoder, which consists of multiple Graph Attention Network (GAT) layers followed by domain-specific normalization (if applicable).
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, data)	Performs a forward pass through the GAT decoder layers and reconstructs the node features.
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)	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)	Registers a backward 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.
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.

Attributes

T_destination
dump_patches
training