Garfield.nn.GCNEncoder

class Garfield.nn.GCNEncoder(in_channels, hidden_dims, latent_dim, use_FCencoder, drop_feature_rate, drop_edge_rate, svd_q, dropout=0.2, num_domains=1, used_edge_weight=False, used_DSBN=False)

The GCNEncoder class implements a Graph Convolutional Network (GCN) encoder with multiple layers, normalization, and optional fully connected (FC) encoder. It supports different types of augmentations for omics and graph data.

forward(data, decoder_type, augment_type)

Performs the forward pass through the GCN encoder, applying either omics or graph decoding, with optional augmentation.

_forward_through_layers(x, edge_index, edge_weight, y)

Helper function to pass the input features through multiple GCN layers and apply normalization.

_apply_normalization(x, y, idx)

Applies batch normalization or domain-specific batch normalization (DSBN) based on the model’s configuration.

Parameters:

• in_channels (int) – Number of input feature dimensions (length of each node’s feature vector).

• hidden_dims (list[int]) – List of output dimensions for each hidden layer in the GCN.

• latent_dim (int) – Dimension of the latent feature representation produced by the encoder.

• use_FCencoder (bool) – Whether to use a fully connected encoder (FC encoder) before the GCN layers.

• drop_feature_rate (float) – Dropout rate for node features during augmentation.

• drop_edge_rate (float) – Dropout rate for edges during augmentation.

• svd_q (int) – Rank for the low-rank SVD approximation used in augmentations.

• dropout (float, optional) – Dropout rate applied to GCN layers, default is 0.2.

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

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

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

__init__(in_channels, hidden_dims, latent_dim, use_FCencoder, drop_feature_rate, drop_edge_rate, svd_q, dropout=0.2, num_domains=1, used_edge_weight=False, used_DSBN=False)

Initializes the GCNEncoder with configurable options for feature projection, dropout, and domain-specific batch normalization (DSBN).

Methods

__init__(in_channels, hidden_dims, ...[, ...])	Initializes the GCNEncoder with configurable options for feature projection, dropout, and domain-specific batch normalization (DSBN).
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(data, decoder_type[, augment_type])	Forward pass through the GCN encoder, with optional augmentations such as dropout or SVD, and multiple decoding options.
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