ConvKB
- class ConvKB(*, embedding_dim: int = 200, hidden_dropout_rate: float = 0.0, num_filters: int = 400, regularizer: ~pykeen.regularizers.Regularizer | None = None, entity_initializer: str | ~collections.abc.Callable[[~torch.Tensor], ~torch.Tensor] | None = <function uniform_>, relation_initializer: str | ~collections.abc.Callable[[~torch.Tensor], ~torch.Tensor] | None = <function uniform_>, **kwargs)[source]
Bases:
ERModel[Tensor,Tensor,Tensor]An implementation of ConvKB from [nguyen2018].
ConvKB represents entities and relations using a \(d\)-dimensional embedding vectors, which are stored as
Embedding.ConvKBInteractionis used to obtain triple scores.See also
Authors’ implementation of ConvKB
Initialize the model.
- Parameters:
embedding_dim (int) – The entity embedding dimension \(d\).
hidden_dropout_rate (float) – The hidden dropout rate
num_filters (int) – The number of convolutional filters to use
regularizer (Regularizer | None) – The regularizer to use. Defaults to \(L_p\)
entity_initializer (str | Callable[[Tensor], Tensor] | None) – Entity initializer function. Defaults to
torch.nn.init.uniform_()relation_initializer (str | Callable[[Tensor], Tensor] | None) – Relation initializer function. Defaults to
torch.nn.init.uniform_()kwargs – Remaining keyword arguments passed through to
ERModel.
To be consistent with the paper, pass entity and relation embeddings pre-trained from TransE.
Attributes Summary
The default strategy for optimizing the model's hyper-parameters
The LP settings used by [nguyen2018] for ConvKB.
Attributes Documentation
- hpo_default: ClassVar[Mapping[str, Any]] = {'embedding_dim': {'high': 256, 'low': 16, 'q': 16, 'type': <class 'int'>}, 'hidden_dropout_rate': {'high': 0.5, 'low': 0.0, 'q': 0.1, 'type': <class 'float'>}, 'num_filters': {'high': 9, 'low': 7, 'scale': 'power_two', 'type': <class 'int'>}}
The default strategy for optimizing the model’s hyper-parameters