class TransE(*, embedding_dim=50, scoring_fct_norm=1, entity_initializer=<function xavier_uniform_>, entity_constrainer=<function normalize>, relation_initializer=<pykeen.utils.compose object>, relation_constrainer=None, regularizer=None, regularizer_kwargs=None, **kwargs)[source]

Bases: ERModel

An implementation of TransE [bordes2013].

TransE models relations as a translation from head to tail entities in \(\textbf{e}\):

\[\textbf{e}_h + \textbf{e}_r \approx \textbf{e}_t\]

This equation is rearranged and the \(l_p\) norm is applied to create the TransE interaction function.

\[f(h, r, t) = - \|\textbf{e}_h + \textbf{e}_r - \textbf{e}_t\|_{p}\]

While this formulation is computationally efficient, it inherently cannot model one-to-many, many-to-one, and many-to-many relationships. For triples \((h,r,t_1), (h,r,t_2) \in \mathcal{K}\) where \(t_1 \neq t_2\), the model adapts the embeddings in order to ensure \(\textbf{e}_h + \textbf{e}_r \approx \textbf{e}_{t_1}\) and \(\textbf{e}_h + \textbf{e}_r \approx \textbf{e}_{t_2}\) which results in \(\textbf{e}_{t_1} \approx \textbf{e}_{t_2}\).

Initialize TransE.

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

  • scoring_fct_norm (int) – The \(l_p\) norm applied in the interaction function. Is usually 1 or 2..

  • entity_initializer (Union[str, Callable[[FloatTensor], FloatTensor], None]) – Entity initializer function.

  • entity_constrainer (Union[str, Callable[[FloatTensor], FloatTensor], None]) – Entity constrainer function.

  • relation_initializer (Union[str, Callable[[FloatTensor], FloatTensor], None]) – Relation initializer function.

  • relation_constrainer (Union[str, Callable[[FloatTensor], FloatTensor], None]) – Relation constrainer function. Defaults to none.

  • kwargs – Remaining keyword arguments to forward to pykeen.models.ERModel.__init__()

  • regularizer (Union[str, Regularizer, Type[Regularizer], None]) – a regularizer, or a hint thereof. Used for both, entity and relation representations; directly use ERModel if you need more flexibility

  • regularizer_kwargs (Optional[Mapping[str, Any]]) – keyword-based parameters for the regularizer

See also

Attributes Summary


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

Attributes Documentation

hpo_default: ClassVar[Mapping[str, Any]] = {'embedding_dim': {'high': 256, 'low': 16, 'q': 16, 'type': <class 'int'>}, 'scoring_fct_norm': {'high': 2, 'low': 1, 'type': <class 'int'>}}

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