torch_concepts.nn.WhitenedEmbeddingToConcept

class WhitenedEmbeddingToConcept(in_embeddings: int | Annotations, out_concepts: int | Annotations, **kwargs)

Concept encoder based on Concept Whitening.

Wraps a ConceptWhitening layer and returns only the concept-aligned axes, so it can be used as a CBM-style bottleneck encoder in PyC pipelines. Note that, unlike the paper’s setting where the task head sees the full whitened embedding, this discards the residual in_embeddings - out_concepts axes; use the wrapped encoder directly to keep them.

Alignment is delegated to the wrapped layer:

enc = WhitenedEmbeddingToConcept(in_embeddings=64, out_concepts=3)
with enc.align(0):
    enc(concept_batch)
enc.update_rotation_matrix()

Parameters:

• in_embeddings – Number of input embedding features.

• out_concepts – Number of output concept representations.

• **kwargs – Additional keyword arguments for ConceptWhitening.

Example

>>> import torch
>>> from torch_concepts.nn import WhitenedEmbeddingToConcept
>>>
>>> enc = WhitenedEmbeddingToConcept(in_embeddings=16, out_concepts=4)
>>> x = torch.randn(8, 16)
>>> concepts = enc(x)
>>> print(concepts.shape)
torch.Size([8, 4])

References

Chen, Bei & Rudin. “Concept whitening for interpretable image recognition”, Nature Machine Intelligence 2020. https://www.nature.com/articles/s42256-020-00265-z

__init__(in_embeddings: int | Annotations, out_concepts: int | Annotations, **kwargs)

Methods

__init__(in_embeddings, out_concepts, **kwargs)
add_module(name, module)	Add a child module to the current module.
align(concept_index)	See ConceptWhitening.align().
annotate(x[, out_concepts])
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(embeddings)	Encode embeddings into concept activations.
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.
prune(mask)	Prune the predictor by removing connections based on the given mask.
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.
update_rotation_matrix([num_updates])	See ConceptWhitening.update_rotation_matrix().
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
call_super_init
dump_patches
training