CP
- class CP(embedding_dim: int = 64, rank: int = 64, entity_initializer: str | Callable[[Tensor], Tensor] | None = None, entity_initializer_kwargs: Mapping[str, Any] | None = None, entity_normalizer: str | Callable[[Tensor], Tensor] | None = None, entity_normalizer_kwargs: Mapping[str, Any] | None = None, relation_initializer: str | Callable[[Tensor], Tensor] | None = None, relation_initializer_kwargs: Mapping[str, Any] | None = None, **kwargs)[source]
Bases:
ERModel[Tensor,Tensor,Tensor]An implementation of CP as described in [lacroix2018] based on [hitchcock1927].
It has separate entity representations for the head and tail role, both a \(r \times d\)-dimensional matrices. Relations are also represented by a \(r \times d\)-dimensional matrix. All three components can be stored as
Embedding.On top of these,
CPInteractionis applied to obtain scores.Initialize the model.
- Parameters:
embedding_dim (int) – The entity embedding dimension \(d\).
rank (int) – The tensor decomposition rank \(k\).
entity_initializer (str | Callable[[Tensor], Tensor] | None) – Entity initializer function. Defaults to None
entity_initializer_kwargs (Mapping[str, Any] | None) – Keyword arguments to be used when calling the entity initializer
entity_normalizer (str | Callable[[Tensor], Tensor] | None) – Entity normalizer function. Defaults to None
entity_normalizer_kwargs (Mapping[str, Any] | None) – Keyword arguments to be used when calling the entity normalizer
relation_initializer (str | Callable[[Tensor], Tensor] | None) – Relation initializer function. Defaults to None
relation_initializer_kwargs (Mapping[str, Any] | None) – Keyword arguments to be used when calling the relation initializer
kwargs – Remaining keyword arguments passed through to
ERModel.
Attributes Summary
The default strategy for optimizing the model's hyper-parameters
Attributes Documentation