Loss Functions

Loss functions integrated in PyKEEN.

Functions

get_loss_cls(query)

Get the loss class.

Classes

BCEAfterSigmoidLoss([reduction])	A loss function which uses the numerically unstable version of explicit Sigmoid + BCE.
SoftplusLoss([reduction])	A loss function for the softplus.
NSSALoss([margin, adversarial_temperature, …])	An implementation of the self-adversarial negative sampling loss function proposed by [sun2019].
CrossEntropyLoss([reduction])	Evaluate cross entropy after softmax output.
MarginRankingLoss([margin, size_average, …])	A wrapper around the PyTorch margin ranking loss.
MSELoss([size_average, reduce, reduction])	A wrapper around the PyTorch mean square error loss.
BCEWithLogitsLoss([weight, size_average, …])	A wrapper around the numeric stable version of the PyTorch binary cross entropy loss.

Class Inheritance Diagram