pyagc.clusters.DECClusterHead

class DECClusterHead(n_clusters: int, n_features: int, alpha: float = 1.0)

Bases: BaseClusterHead

Neural Clustering Layer proposed in the “Unsupervised Deep Embedding for Clustering Analysis” paper (Xie et al., ICML 2016).

This layer learns cluster centers and computes soft assignment of input samples to clusters using Student’s t-distribution.

Specifically, the probability \(q_{ij}\) that a sample \(i\) belongs to cluster \(j\) is given by:

\[q_{ij} = \frac{(1 + \|z_i - \mu_j\|^2 / \alpha)^{-\frac{\alpha+1}{2}}} {\sum_{j'} (1 + \|z_i - \mu_{j'}\|^2 / \alpha)^{-\frac{\alpha+1}{2}}}\]

where \(z_i\) is the embedded point and \(\mu_j\) is the j-th cluster center, and \(\alpha\) is the degrees of freedom of the Student’s t-distribution (default is 1).

The target distribution \(p_{ij}\) is computed as:

\[p_{ij} = \frac{q_{ij}^2 / \sum_i q_{ij}}{\sum_j (q_{ij}^2 / \sum_i q_{ij})}\]

The loss is the KL divergence between the soft assignments \(q\) and the target distribution \(p\):

\[L = \text{KL}(P \| Q) = \sum_i \sum_j p_{ij} \log \frac{p_{ij}}{q_{ij}}\]

Parameters:

• n_clusters (int) – Number of clusters.

• n_features (int) – Feature dimension of the input.

• alpha (float, optional) – Degrees of freedom for Student’s t-distribution. Default is 1.

__init__(n_clusters: int, n_features: int, alpha: float = 1.0)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Methods

__init__(n_clusters, n_features[, alpha])	Initialize internal Module state, shared by both nn.Module and ScriptModule.
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.
cluster(z[, soft])	Predicts cluster assignments.
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(z[, update_target])	Computes the KL divergence loss between the soft assignments and the target distribution.
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()	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.
reset_cluster_centers([cluster_centers])	Manually sets the cluster centers.
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.

Attributes

T_destination	alias of TypeVar('T_destination', bound=dict[str, Any])
call_super_init
dump_patches
predict	Alias for cluster().

reset_cluster_centers(cluster_centers: Optional[Tensor] = None) → None

Manually sets the cluster centers.

Parameters:

cluster_centers (torch.Tensor, optional) – Tensor of shape (n_clusters, n_features) to initialize the cluster centers. If None, use Xavier uniform initialization.

Return type:

None

forward(z: Tensor, update_target: bool = True) → Tensor

Computes the KL divergence loss between the soft assignments and the target distribution.

Parameters:

• z (torch.Tensor) – Input tensor of shape (n_samples, n_features).

• update_target (bool, optional) – Whether to recompute the target distribution P. If False, uses the cached distribution. This is useful for maintaining training stability by updating the target less frequently. (default: True)

Returns:

Tensor – Scalar loss tensor.

cluster(z: Tensor, soft: bool = False) → Tensor

Predicts cluster assignments.

Parameters:

• z (torch.Tensor) – Input tensor of shape (n_samples, n_features).

• soft (bool, optional) – If True, returns the soft assignment matrix; if False, returns hard cluster assignments. (default: False)

Returns:

Tensor –:

• If soft is False, (n_samples,) tensor of cluster indices.

• If soft is True, (n_samples, n_clusters) tensor of probabilities.