ComplExLiteral

class ComplExLiteral(triples_factory, embedding_dim=50, automatic_memory_optimization=None, input_dropout=0.2, loss=None, preferred_device=None, random_seed=None)

Bases: pykeen.models.base.MultimodalModel

An implementation of ComplexLiteral from [agustinus2018] based on the LCWA training approach.

Initialize the model.

Attributes Summary

hpo_default	The default strategy for optimizing the model’s hyper-parameters
loss_default_kwargs	The default parameters for the default loss function class

Methods Summary

score_t(doubles)

Forward pass using right side (tail) prediction for training with the LCWA.

Attributes Documentation

hpo_default: ClassVar[Mapping[str, Any]] = {'embedding_dim': {'high': 300, 'low': 50, 'q': 50, 'type': <class 'int'>}, 'input_dropout': {'high': 0.3, 'low': 0.1, 'type': <class 'float'>}}

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

loss_default_kwargs: ClassVar[Optional[Mapping[str, Any]]] = {}

The default parameters for the default loss function class

Methods Documentation

score_t(doubles)

Forward pass using right side (tail) prediction for training with the LCWA.

Return type

Tensor