PairRE

class PairRE(embedding_dim=200, p=1, power_norm=False, entity_initializer=<function uniform_>, entity_initializer_kwargs=None, entity_normalizer=<function normalize>, entity_normalizer_kwargs=None, relation_initializer=<function uniform_>, relation_initializer_kwargs=None, **kwargs)

Bases: ERModel

An implementation of PairRE from [chao2020].

Initialize PairRE via the pykeen.nn.modules.PairREInteraction interaction.

Parameters:

• embedding_dim (int) – The entity embedding dimension \(d\).

• p (int) – The \(l_p\) norm.

• power_norm (bool) – Should the power norm be used?

• entity_initializer (Union[str, Callable[[FloatTensor], FloatTensor], None]) – Entity initializer function. Defaults to torch.nn.init.uniform_()

• entity_initializer_kwargs (Optional[Mapping[str, Any]]) – Keyword arguments to be used when calling the entity initializer

• entity_normalizer (Union[str, Callable[[FloatTensor], FloatTensor], None]) – Entity normalizer function. Defaults to torch.nn.functional.normalize()

• entity_normalizer_kwargs (Optional[Mapping[str, Any]]) – Keyword arguments to be used when calling the entity normalizer

• relation_initializer (Union[str, Callable[[FloatTensor], FloatTensor], None]) – Relation initializer function. Defaults to torch.nn.init.uniform_()

• relation_initializer_kwargs (Optional[Mapping[str, Any]]) – Keyword arguments to be used when calling the relation initializer

• kwargs – Remaining keyword arguments passed through to pykeen.models.ERModel.

Attributes Summary

default_entity_normalizer_kwargs	The default entity normalizer parameters The entity representations are normalized to L2 unit length cf.
hpo_default	The default strategy for optimizing the model's hyper-parameters
loss_default_kwargs	The default parameters for the default loss function class

Attributes Documentation

default_entity_normalizer_kwargs: ClassVar[Mapping[str, Any]] = {'dim': -1, 'p': 2}

The default entity normalizer parameters The entity representations are normalized to L2 unit length cf. https://github.com/alipay/KnowledgeGraphEmbeddingsViaPairedRelationVectors_PairRE/blob/0a95bcd54759207984c670af92ceefa19dd248ad/biokg/model.py#L232-L240 # noqa: E501

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

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

loss_default_kwargs: ClassVar[Mapping[str, Any] | None] = {'adversarial_temperature': 1.0, 'margin': 12.0, 'reduction': 'mean'}

The default parameters for the default loss function class