UM

class UM(*, embedding_dim: int = 50, scoring_fct_norm: int = 1, power_norm: bool = False, entity_initializer: str | ~typing.Callable[[~torch.Tensor], ~torch.Tensor] | None = <function xavier_normal_>, **kwargs)

Bases: ERModel[Tensor, tuple[()], Tensor]

An implementation of the Unstructured Model (UM) published by [bordes2014].

This model represents entities as \(d\)-dimensional vectors stored in Embedding. It does not have any relation representations. The UMInteraction is used to calculate scores.

Initialize UM.

Parameters:

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

• scoring_fct_norm (int) – The norm used with torch.linalg.vector_norm(). Typically is 1 or 2.

• power_norm (bool) – Whether to use the p-th power of the \(L_p\) norm. It has the advantage of being differentiable around 0, and numerically more stable.

• entity_initializer (str | Callable[[Tensor], Tensor] | None) – The initializer for the entity embeddings. Defaults to pykeen.nn.init.xavier_normal().

• kwargs – Remaining keyword arguments passed through to ERModel.

Attributes Summary

hpo_default

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