torch_concepts.nn.MixConceptEmbeddingToConcept

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

Concept predictor that mixes concept activations with embeddings.

This predictor implements the Concept Embedding Model (CEM) task predictor that combines concept activations with learned embeddings using a mixture operation.

Main reference: “Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off” (Espinosa Zarlenga et al., NeurIPS 2022).

in_concepts

Number of input concepts.

Type:

int

in_embeddings

Number of embedding features.

Type:

int

out_concepts

Number of output concepts.

Type:

int

cardinalities

Cardinalities for grouped concepts.

Type:

List[int]

predictor

Linear predictor module.

Type:

nn.Module

Parameters:

• in_concepts – Number of input concepts.

• in_embeddings – Number of embedding features (must be even).

• out_concepts – Number of output concepts.

• cardinalities – List of concept group cardinalities. Required — must sum to in_concepts.

Example

>>> import torch
>>> from torch_concepts.nn import MixConceptEmbeddingToConcept
>>> from torch_concepts import Annotations
>>>
>>> # Create predictor: 3 concepts (cardinalities 3, 4, 3), 10 embedding dims, 2 outputs
>>> in_ann = Annotations(labels=['color', 'shape', 'size'], cardinalities=[3, 4, 3])
>>> predictor = MixConceptEmbeddingToConcept(
...     in_concepts=in_ann,
...     in_embeddings=10,
...     out_concepts=2,
... )
>>>
>>> # Generate random inputs
>>> concepts = torch.randn(4, 10)  # batch_size=4, total logits (3+4+3=10)
>>> embeddings = torch.randn(4, 10, 10)  # (batch, total_cardinality, emb_size)
>>>
>>> # Forward pass
>>> output = predictor(concepts=concepts, embeddings=embeddings)
>>> print(output.shape)
torch.Size([4, 2])

References

Espinosa Zarlenga et al. “Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off”, NeurIPS 2022. https://arxiv.org/abs/2209.09056

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

Methods

__init__(in_concepts, in_embeddings, ...)
add_module(name, module)	Add a child module to the current module.
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(concepts, embeddings)	Forward pass through the predictor.
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.
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