torch_concepts.nn.WANDAGraphLearner¶

class WANDAGraphLearner(row_labels: List[str], col_labels: List[str], priority_var: float = 1.0, hard_threshold: bool = True, threshold_init: float = 0.0, eps: float = 1e-12)[source]¶

WANDA Graph Learner for concept structure discovery. Adapted from COSMO.

WANDA learns a directed acyclic graph (DAG) structure by assigning priority values to concepts and creating edges based on priority differences. This approach ensures acyclicity by construction.

np_params¶

Learnable priority values for each concept.

Type:: nn.Parameter

priority_var¶

Variance for priority initialization.

Type:: float

threshold¶

Fixed threshold for edge creation (not learnable).

Type:: torch.Tensor

hard_threshold¶

Whether to use hard or soft thresholding.

Type:: bool

Parameters:

row_labels – List of concept names for graph rows.
col_labels – List of concept names for graph columns.
priority_var – Variance for priority initialization (default: 1.0).
hard_threshold – Use hard thresholding for edges (default: True).
threshold_init – Initial value for threshold (default: 0.0).

Example

>>> import torch
>>> from torch_concepts.nn import WANDAGraphLearner
>>>
>>> # Create WANDA learner for 5 concepts
>>> concepts = ['c1', 'c2', 'c3', 'c4', 'c5']
>>> wanda = WANDAGraphLearner(
...     row_labels=concepts,
...     col_labels=concepts,
...     priority_var=1.0,
...     hard_threshold=True,
...     threshold_init=0.5
... )
>>>
>>> # Get current graph estimate
>>> adj_matrix = wanda.weighted_adj
>>> print(adj_matrix.shape)
torch.Size([5, 5])

References

Massidda et al. “Constraint-Free Structure Learning with Smooth Acyclic Orientations”. https://arxiv.org/abs/2309.08406

__init__(row_labels: List[str], col_labels: List[str], priority_var: float = 1.0, hard_threshold: bool = True, threshold_init: float = 0.0, eps: float = 1e-12)[source]¶

Initialize the WANDA graph learner.

Parameters:

row_labels – List of concept names for graph rows.
col_labels – List of concept names for graph columns.
priority_var – Variance for priority initialization (default: 1.0).
hard_threshold – Use hard thresholding for edges (default: True).
threshold_init – Initial value for threshold (default: 0.0).
eps – Small epsilon value for numerical stability (default: 1e-12).

Methods

`__init__`(row_labels, col_labels[, ...])	Initialize the WANDA graph learner.
`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`(*input)	Define the computation performed at every call.
`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.
`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`
`weighted_adj`	Compute the weighted adjacency matrix from learned priorities.
`training`