# SoftplusLoss

class SoftplusLoss(reduction='mean')[source]

The pointwise logistic loss (i.e., softplus loss).

$g(s, l) = \log(1 + \exp(-\hat{l} \cdot s))$

with scores $$s$$ and labels $$l$$ that have been rescaled to $$\hat{l} \in \{-1, 1\}$$.

This class is a special case of pykeen.losses.SoftPointwiseHingeLoss where the margin is set to margin=0.

Initialize the loss.

Parameters

reduction (str) – the reduction, cf. SoftPointwiseHingeLoss.__init__()

Attributes Summary

 hpo_default The default strategy for optimizing the loss's hyper-parameters

Attributes Documentation

hpo_default: ClassVar[Mapping[str, Any]] = {}

The default strategy for optimizing the loss’s hyper-parameters