OrthogonalityRegularizer

class OrthogonalityRegularizer(*, weight=1.0, apply_only_once=True, epsilon=1e-05, **kwargs)[source]

Bases: Regularizer

A regularizer for the soft orthogonality constraints from [wang2014].

Initialize the regularizer.

Parameters
  • weight (float) – The relative weight of the regularization

  • apply_only_once (bool) – Should the regularization be applied more than once after reset?

  • epsilon (float) – a small value used to check for approximate orthogonality

  • kwargs – additional keyword-based parameters passed to Regularizer.__init__()

Attributes Summary

hpo_default

The default strategy for optimizing the TransH regularizer's hyper-parameters

Methods Summary

forward(x)

Compute the regularization term for one tensor.

update(*tensors)

Update the regularization term based on passed tensors.

Attributes Documentation

hpo_default: ClassVar[Mapping[str, Any]] = {'weight': {'high': 1.0, 'low': 0.01, 'scale': 'log', 'type': <class 'float'>}}

The default strategy for optimizing the TransH regularizer’s hyper-parameters

Methods Documentation

forward(x)[source]

Compute the regularization term for one tensor.

Return type

FloatTensor

Parameters

x (FloatTensor) –

update(*tensors)[source]

Update the regularization term based on passed tensors.

Return type

None

Parameters

tensors (FloatTensor) –