torch_concepts.nn.ForwardInference

class ForwardInference(probabilistic_model: ProbabilisticModel, graph_learner: BaseGraphLearner | None = None, *args, **kwargs)

Forward inference engine for probabilistic models.

This class implements forward inference through a probabilistic model by topologically sorting variables and computing them in dependency order. It supports parallel computation within topological levels and can optionally use a learned graph structure.

The inference engine: - Automatically sorts variables in topological order - Computes variables level-by-level (variables at same depth processed in parallel) - Supports GPU parallelization via CUDA streams - Supports CPU parallelization via threading - Handles interventions via _InterventionWrapper

probabilistic_model

The probabilistic model to perform inference on.

Type:

ProbabilisticModel

graph_learner

Optional graph structure learner.

Type:

BaseGraphLearner

concept_map

Maps concept names to Variable objects.

Type:

Dict[str, Variable]

sorted_variables

Variables in topological order.

Type:

List[Variable]

levels

Variables grouped by topological depth.

Type:

List[List[Variable]]

Parameters:

• probabilistic_model – The probabilistic model to perform inference on.

• graph_learner – Optional graph learner for weighted adjacency structure.

Raises:

RuntimeError – If the model contains cycles (not a DAG).

Example

>>> import torch
>>> from torch.distributions import Bernoulli
>>> from torch_concepts import InputVariable, EndogenousVariable
>>> from torch_concepts.distributions import Delta
>>> from torch_concepts.nn import ForwardInference, ParametricCPD, ProbabilisticModel
>>>
>>> # Create a simple model: latent -> A -> B
>>> # Where A is a root concept and B depends on A
>>>
>>> # Define variables
>>> input_var = InputVariable('input', parents=[], distribution=Delta, size=10)
>>> var_A = EndogenousVariable('A', parents=['input'], distribution=Bernoulli, size=1)
>>> var_B = EndogenousVariable('B', parents=['A'], distribution=Bernoulli, size=1)
>>>
>>> # Define CPDs (modules that compute each variable)
>>> from torch.nn import Identity, Linear
>>> latent_cpd = ParametricCPD('input', parametrization=Identity())
>>> cpd_A = ParametricCPD('A', parametrization=Linear(10, 1))  # latent -> A
>>> cpd_B = ParametricCPD('B', parametrization=Linear(1, 1))   # A -> B
>>>
>>> # Create probabilistic model
>>> pgm = ProbabilisticModel(
...     variables=[input_var, var_A, var_B],
...     parametric_cpds=[latent_cpd, cpd_A, cpd_B]
... )
>>>
>>> # Create forward inference engine
>>> inference = ForwardInference(pgm)
>>>
>>> # Check topological order
>>> print([v.concepts[0] for v in inference.sorted_variables])
>>> # ['input', 'A', 'B']
>>>
>>> # Check levels (for parallel computation)
>>> for i, level in enumerate(inference.levels):
...     print(f"Level {i}: {[v.concepts[0] for v in level]}")
>>> # Level 0: ['input']
>>> # Level 1: ['A']
>>> # Level 2: ['B']

__init__(probabilistic_model: ProbabilisticModel, graph_learner: BaseGraphLearner | None = None, *args, **kwargs)

Initialize the inference module.

Methods

__init__(probabilistic_model[, graph_learner])	Initialize the inference module.
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(x, *args, **kwargs)	Forward pass delegates to the query method.
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_parent_kwargs(parametric_cpd[, ...])	Prepare keyword arguments for CPD forward pass based on parent outputs.
get_results(results, parent_variable)	Process the raw output tensor from a CPD.
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.
predict(external_inputs[, debug, device])	Perform forward pass prediction across the entire probabilistic model.
query(query_concepts, evidence[, debug, device])	Execute forward pass and return only specified concepts concatenated.
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.
unrolled_probabilistic_model()	Build an 'unrolled' view of the ProbabilisticModel based on graph_learner adjacency.
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
available_query_vars	Get all variable names available for querying.
call_super_init
dump_patches
training