DistMultLiteral

class DistMultLiteral(triples_factory, embedding_dim=50, input_dropout=0.0, loss=None, preferred_device=None, random_seed=None)

Bases: pykeen.models.unimodal.distmult.DistMult, pykeen.models.base.MultimodalModel

An implementation of DistMultLiteral from [kristiadi2018].

Initialize DistMult.

Parameters

• embedding_dim (int) – The entity embedding dimension \(d\). Is usually \(d \in [50, 300]\).

• entity_initializer – Default: xavier uniform, c.f. https://github.com/thunlp/OpenKE/blob/adeed2c0d2bef939807ed4f69c1ea4db35fd149b/models/DistMult.py#L16-L17

• entity_constrainer – Default: constrain entity embeddings to unit length

• relation_initializer – Default: relations are initialized to unit length (but not constrained)

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

forward(h_indices, r_indices, t_indices)

Defines the computation performed at every call.

Attributes Documentation

hpo_default: ClassVar[Mapping[str, Any]] = {'embedding_dim': {'high': 256, 'low': 16, 'q': 16, 'type': <class 'int'>}, 'input_dropout': {'high': 0.5, 'low': 0.0, 'q': 0.1, 'type': <class 'float'>}}

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

loss_default_kwargs: ClassVar[Mapping[str, Any]] = {'margin': 0.0}

The default parameters for the default loss function class

Methods Documentation

forward(h_indices, r_indices, t_indices)

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