torch_concepts.nn.MixCUC

class MixCUC(in_features_endogenous: int, in_features_exogenous: int, out_features: int, in_activation: ~typing.Callable = <built-in method sigmoid of type object>, cardinalities: ~typing.List[int] | None = None)

Concept exogenous predictor with mixture of concept activations and exogenous features.

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

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

in_features_endogenous

Number of input concept endogenous.

Type:

int

in_features_exogenous

Number of exogenous features.

Type:

int

out_features

Number of output features.

Type:

int

cardinalities

Cardinalities for grouped concepts.

Type:

List[int]

predictor

Linear predictor module.

Type:

nn.Module

Parameters:

• in_features_endogenous – Number of input concept endogenous.

• in_features_exogenous – Number of exogenous features (must be even).

• out_features – Number of output task features.

• in_activation – Activation function for concept endogenous (default: sigmoid).

• cardinalities – List of concept group cardinalities (optional).

Example

>>> import torch
>>> from torch_concepts.nn import MixCUC
>>>
>>> # Create predictor with 10 concepts, 20 exogenous dims, 3 tasks
>>> predictor = MixCUC(
...     in_features_endogenous=10,
...     in_features_exogenous=10,  # Must be half of exogenous latent size when no cardinalities are provided
...     out_features=3,
...     in_activation=torch.sigmoid
... )
>>>
>>> # Generate random inputs
>>> concept_endogenous = torch.randn(4, 10)  # batch_size=4, n_concepts=10
>>> exogenous = torch.randn(4, 10, 20)  # (batch, n_concepts, emb_size)
>>>
>>> # Forward pass
>>> task_endogenous = predictor(endogenous=concept_endogenous, exogenous=exogenous)
>>> print(task_endogenous.shape)  # torch.Size([4, 3])
>>>
>>> # With concept groups (e.g., color has 3 values, shape has 4, etc.)
>>> predictor_grouped = MixCUC(
...     in_features_endogenous=10,
...     in_features_exogenous=20, # Must be equal to exogenous latent size when cardinalities are provided
...     out_features=3,
...     cardinalities=[3, 4, 3]  # 3 groups summing to 10
... )
>>>
>>> # Forward pass with grouped concepts
>>> task_endogenous = predictor_grouped(endogenous=concept_endogenous, exogenous=exogenous)
>>> print(task_endogenous.shape)  # torch.Size([4, 3])

References

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

__init__(in_features_endogenous: int, in_features_exogenous: int, out_features: int, in_activation: ~typing.Callable = <built-in method sigmoid of type object>, cardinalities: ~typing.List[int] | None = None)

Methods

__init__(in_features_endogenous, ...[, ...])
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.
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(endogenous, exogenous)	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()	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