SoftPointwiseHingeLoss
- class SoftPointwiseHingeLoss(margin: float = 1.0, reduction: Literal['mean', 'sum'] = 'mean')[source]
Bases:
DeltaPointwiseLoss
The soft pointwise hinge loss.
This loss is appropriate for interaction functions which do not include a bias term, and have a limited value range, e.g., distance-based ones like TransE.
See also
When choosing
margin=0
, this loss becomes equivalent topykeen.losses.SoftplusLoss
. It is also closely related topykeen.losses.PointwiseHingeLoss
, only differing in that this loss uses the softmax activation andpykeen.losses.PointwiseHingeLoss
uses the ReLU activation.Initialize the loss.
- Parameters:
margin (float) – the margin, cf.
DeltaPointwiseLoss.__init__()
reduction (Reduction) – the reduction, cf.
DeltaPointwiseLoss.__init__()
Attributes Summary
The default strategy for optimizing the loss's hyper-parameters
Attributes Documentation