torch_concepts.nn.CallableCC¶

class CallableCC(func: ~typing.Callable, in_activation: ~typing.Callable = <function CallableCC.<lambda>>, use_bias: bool = True, init_bias_mean: float = 0.0, init_bias_std: float = 0.01, min_std: float = 1e-06)[source]¶

A predictor that applies a custom callable function to concept representations.

This predictor allows flexible task prediction by accepting any callable function that operates on concept representations. It optionally includes learnable stochastic bias parameters (mean and standard deviation) that are added to the output using the reparameterization trick for gradient-based learning.

The module can be used to write custom layers for standard Structural Causal Models (SCMs).

Parameters:

func – Callable function that takes concept probabilities and returns task predictions. Should accept a tensor of shape (batch_size, n_concepts) and return a tensor of shape (batch_size, out_features).
in_activation – Activation function to apply to input endogenous before passing to func. Default is identity (lambda x: x).
use_bias – Whether to add learnable stochastic bias to the output. Default is True.
init_bias_mean – Initial value for the bias mean parameter. Default is 0.0.
init_bias_std – Initial value for the bias standard deviation. Default is 0.01.
min_std – Minimum standard deviation floor for numerical stability. Default is 1e-6.

Examples

>>> import torch
>>> from torch_concepts.nn import CallableCC
>>>
>>> # Generate sample data
>>> batch_size = 32
>>> n_concepts = 3
>>> endogenous = torch.randn(batch_size, n_concepts)
>>>
>>> # Define a polynomial function with fixed weights for 3 inputs, 2 outputs
>>> def quadratic_predictor(probs):
...     c0, c1, c2 = probs[:, 0:1], probs[:, 1:2], probs[:, 2:3]
...     output1 = 0.5*c0**2 + 1.0*c1**2 + 1.5*c2
...     output2 = 2.0*c0 - 1.0*c1**2 + 0.5*c2**3
...     return torch.cat([output1, output2], dim=1)
>>>
>>> predictor = CallableCC(
...     func=quadratic_predictor,
...     use_bias=True
... )
>>> predictions = predictor(endogenous)
>>> print(predictions.shape)  # torch.Size([32, 2])

References: Pearl, J. “Causality”, Cambridge University Press (2009).

__init__(func: ~typing.Callable, in_activation: ~typing.Callable = <function CallableCC.<lambda>>, use_bias: bool = True, init_bias_mean: float = 0.0, init_bias_std: float = 0.01, min_std: float = 1e-06)[source]¶

Methods

`__init__`(func[, in_activation, use_bias, ...])
`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, args, *kwargs)	Forward pass through the concept layer.
`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`