TransE
- class TransE(*, embedding_dim=50, scoring_fct_norm=1, entity_initializer=<function xavier_uniform_>, entity_constrainer=<function normalize>, relation_initializer=<pykeen.utils.compose object>, relation_constrainer=None, **kwargs)[source]
Bases:
pykeen.models.base.EntityRelationEmbeddingModel
An implementation of TransE [bordes2013].
TransE models relations as a translation from head to tail entities in \(\textbf{e}\):
\[\textbf{e}_h + \textbf{e}_r \approx \textbf{e}_t\]This equation is rearranged and the \(l_p\) norm is applied to create the TransE interaction function.
\[f(h, r, t) = - \|\textbf{e}_h + \textbf{e}_r - \textbf{e}_t\|_{p}\]While this formulation is computationally efficient, it inherently cannot model one-to-many, many-to-one, and many-to-many relationships. For triples \((h,r,t_1), (h,r,t_2) \in \mathcal{K}\) where \(t_1 \neq t_2\), the model adapts the embeddings in order to ensure \(\textbf{e}_h + \textbf{e}_r \approx \textbf{e}_{t_1}\) and \(\textbf{e}_h + \textbf{e}_r \approx \textbf{e}_{t_2}\) which results in \(\textbf{e}_{t_1} \approx \textbf{e}_{t_2}\).
Initialize TransE.
- Parameters
embedding_dim (
int
) – The entity embedding dimension \(d\). Is usually \(d \in [50, 300]\).scoring_fct_norm (
int
) – The \(l_p\) norm applied in the interaction function. Is usually1
or2.
.entity_initializer (
Union
[str
,Callable
[[FloatTensor
],FloatTensor
],None
]) – Entity initializer function. Defaults topykeen.nn.init.xavier_uniform_()
entity_constrainer (
Union
[str
,Callable
[[FloatTensor
],FloatTensor
],None
]) – Entity constrainer function. Defaults totorch.nn.init.normalize()
relation_initializer (
Union
[str
,Callable
[[FloatTensor
],FloatTensor
],None
]) – Relation initializer function. Defaults topykeen.nn.init.xavier_uniform_norm_()
relation_constrainer (
Union
[str
,Callable
[[FloatTensor
],FloatTensor
],None
]) – Relation constrainer function. Defaults to none.kwargs – Remaining keyword arguments to forward to
pykeen.models.EntityRelationEmbeddingModel
See also
OpenKE implementation of TransE
Attributes Summary
The default strategy for optimizing the model's hyper-parameters
Methods Summary
score_h
(rt_batch)Forward pass using left side (head) prediction.
score_hrt
(hrt_batch)Forward pass.
score_t
(hr_batch)Forward pass using right side (tail) prediction.
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
Methods Documentation
- score_h(rt_batch)[source]
Forward pass using left side (head) prediction.
This method calculates the score for all possible heads for each (relation, tail) pair.
- Parameters
rt_batch (
LongTensor
) – shape: (batch_size, 2), dtype: long The indices of (relation, tail) pairs.- Return type
FloatTensor
- Returns
shape: (batch_size, num_entities), dtype: float For each r-t pair, the scores for all possible heads.
- score_hrt(hrt_batch)[source]
Forward pass.
This method takes head, relation and tail of each triple and calculates the corresponding score.
- Parameters
hrt_batch (
LongTensor
) – shape: (batch_size, 3), dtype: long The indices of (head, relation, tail) triples.- Raises
NotImplementedError – If the method was not implemented for this class.
- Return type
FloatTensor
- Returns
shape: (batch_size, 1), dtype: float The score for each triple.
- score_t(hr_batch)[source]
Forward pass using right side (tail) prediction.
This method calculates the score for all possible tails for each (head, relation) pair.
- Parameters
hr_batch (
LongTensor
) – shape: (batch_size, 2), dtype: long The indices of (head, relation) pairs.- Return type
FloatTensor
- Returns
shape: (batch_size, num_entities), dtype: float For each h-r pair, the scores for all possible tails.