# PairwiseLogisticLoss

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

The pairwise logistic loss.

$L(k, \bar{k}) = \log(1 + \exp(f(\bar{k}) - f(k)))$

Where $$k$$ are the positive triples, $$\bar{k}$$ are the negative triples, $$f$$ is the interaction function (e.g., pykeen.models.TransE has $$f(h,r,t)=-||\mathbf{e}_h+\mathbf{e}_r-\mathbf{e}_t||_p$$), $$g(x)=\log(1 + \exp(x))$$ is the softmax activation function.

This loss is equivalent to pykeen.losses.SoftMarginRankingLoss where margin=0. It is also closely related to pykeen.losses.MarginRankingLoss based on the choice of activation function.

Initialize the loss.

Parameters:

reduction (str) – the reduction, cf. SoftMarginRankingLoss.__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