DistMultLiteral¶

class DistMultLiteral(triples_factory, embedding_dim=50, automatic_memory_optimization=None, input_dropout=0.0, loss=None, preferred_device=None, random_seed=None)[source]¶

Bases: pykeen.models.base.MultimodalModel

An implementation of DistMultLiteral from [agustinus2018].

Initialize the entity embedding model.

Parameters: relation_dim – The relation embedding dimensionality. If not given, defaults to same size as entity embedding dimension.

See also

Constructor of the base class pykeen.models.EntityEmbeddingModel

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

`compute_mr_loss`(positive_scores, negative_scores)	Compute the mean ranking loss for the positive and negative scores.
`score_t`(hr_batch)	Forward pass using right side (tail) prediction for training with the LCWA.

Attributes Documentation

hpo_default: ClassVar[Mapping[str, Any]] = {'embedding_dim': {'high': 350, 'low': 50, 'q': 25, 'type': <class 'int'>}, 'input_dropout': {'high': 1.0, 'low': 0, 'type': <class 'float'>}}¶: The default strategy for optimizing the model’s hyper-parameters

loss_default_kwargs: ClassVar[Optional[Mapping[str, Any]]] = {'margin': 0.0}¶: The default parameters for the default loss function class

Methods Documentation

compute_mr_loss(positive_scores, negative_scores)[source]¶

Compute the mean ranking loss for the positive and negative scores.

Return type: Tensor

score_t(hr_batch)[source]¶

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

Return type: Tensor