TransF
- class TransF(embedding_dim=128, entity_initializer=None, entity_initializer_kwargs=None, entity_normalizer=None, entity_normalizer_kwargs=None, relation_initializer=None, relation_initializer_kwargs=None, **kwargs)[source]
Bases:
pykeen.models.nbase.ERModel
An implementation of TransF from [feng2016].
Initialize TransF via the
pykeen.nn.modules.TransFInteraction
interaction.- Parameters
embedding_dim (
int
) – The entity embedding dimension \(d\).entity_initializer (
Union
[str
,Callable
[[FloatTensor
],FloatTensor
],None
]) – Entity initializer function. Defaults totorch.nn.init.uniform_()
entity_initializer_kwargs (
Optional
[Mapping
[str
,Any
]]) – Keyword arguments to be used when calling the entity initializerentity_normalizer (
Union
[str
,Callable
[[FloatTensor
],FloatTensor
],None
]) – Entity normalizer function. Defaults totorch.nn.functional.normalize()
entity_normalizer_kwargs (
Optional
[Mapping
[str
,Any
]]) – Keyword arguments to be used when calling the entity normalizerrelation_initializer (
Union
[str
,Callable
[[FloatTensor
],FloatTensor
],None
]) – Relation initializer function. Defaults totorch.nn.init.uniform_()
relation_initializer_kwargs (
Optional
[Mapping
[str
,Any
]]) – Keyword arguments to be used when calling the relation initializerkwargs – Remaining keyword arguments passed through to
pykeen.models.ERModel
.
Attributes Summary
The default strategy for optimizing the model's hyper-parameters
Attributes Documentation