Regularizers¶
Regularization in PyKEEN.
Classes¶
|
A simple L_p norm based regularizer. |
|
A regularizer which does not perform any regularization. |
|
A convex combination of regularizers. |
|
A simple x^p based regularizer. |
|
A regularizer for the soft constraints in TransH. |
Class Inheritance Diagram¶
Base Classes¶
-
class
Regularizer
(weight=1.0, apply_only_once=False, parameters=None)[source]¶ A base class for all regularizers.
Instantiate the regularizer.
- Parameters
weight (
float
) – The relative weight of the regularizationapply_only_once (
bool
) – Should the regularization be applied more than once after reset?parameters (
Optional
[Iterable
[Parameter
]]) – Specific parameters to track. if none given, it’s expected that your model automatically delegates to theupdate()
function.
-
apply_only_once
: bool¶ Should the regularization only be applied once? This was used for ConvKB and defaults to False.
-
abstract
forward
(x)[source]¶ Compute the regularization term for one tensor.
- Return type
FloatTensor
-
classmethod
get_normalized_name
()[source]¶ Get the normalized name of the regularizer class.
- Return type
-
hpo_default
: ClassVar[Mapping[str, Any]]¶ The default strategy for optimizing the regularizer’s hyper-parameters
-
pop_regularization_term
()[source]¶ Return the weighted regularization term, and reset the regularize afterwards.
- Return type
FloatTensor
-
regularization_term
: torch.FloatTensor¶ The current regularization term (a scalar)
-
property
term
¶ Return the weighted regularization term.
- Return type
FloatTensor
-
weight
: torch.FloatTensor¶ The overall regularization weight