MSELoss

class MSELoss(reduction='mean')

Bases: PointwiseLoss

The mean squared error loss.

Note

The related torch module is torch.nn.MSELoss, but it can not be used interchangeably in PyKEEN because of the extended functionality implemented in PyKEEN’s loss functions.

Initialize the loss.

Parameters:

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

Attributes Summary

synonyms

synonyms of this loss

Methods Summary

forward(scores, labels)

Defines the computation performed at every call.

Attributes Documentation

synonyms: ClassVar[Set[str] | None] = {'Mean Square Error Loss', 'Mean Squared Error Loss'}

synonyms of this loss

Methods Documentation

forward(scores, labels)

Defines the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

Return type:

FloatTensor

Parameters:

• scores (FloatTensor) –

• labels (FloatTensor) –