TransR¶
-
class
TransR
(triples_factory, embedding_dim=50, relation_dim=30, scoring_fct_norm=1, loss=None, preferred_device=None, random_seed=None, regularizer=None, entity_initializer=<function xavier_uniform_>, entity_constrainer=<function clamp_norm>, relation_initializer=<pykeen.utils.compose object>, relation_constrainer=<function clamp_norm>)[source]¶ Bases:
pykeen.models.base.EntityRelationEmbeddingModel
An implementation of TransR from [lin2015].
TransR is an extension of
pykeen.models.TransH
that explicitly considers entities and relations as different objects and therefore represents them in different vector spaces.For a triple \((h,r,t) \in \mathbb{K}\), the entity embeddings, \(\textbf{e}_h, \textbf{e}_t \in \mathbb{R}^d\), are first projected into the relation space by means of a relation-specific projection matrix \(\textbf{M}_{r} \in \mathbb{R}^{k \times d}\). With relation embedding \(\textbf{r}_r \in \mathbb{R}^k\), the interaction model is defined similarly to TransE with:
\[f(h,r,t) = -\|\textbf{M}_{r}\textbf{e}_h + \textbf{r}_r - \textbf{M}_{r}\textbf{e}_t\|_{p}^2\]The following constraints are applied:
\(\|\textbf{e}_h\|_2 \leq 1\)
\(\|\textbf{r}_r\|_2 \leq 1\)
\(\|\textbf{e}_t\|_2 \leq 1\)
\(\|\textbf{M}_{r}\textbf{e}_h\|_2 \leq 1\)
\(\|\textbf{M}_{r}\textbf{e}_t\|_2 \leq 1\)
See also
Initialize the model.
Attributes Summary
The default strategy for optimizing the model’s hyper-parameters
Methods Summary
interaction_function
(h, r, t, m_r)Evaluate the interaction function for given embeddings.
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'>}, 'relation_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
-
static
interaction_function
(h, r, t, m_r)[source]¶ Evaluate the interaction function for given embeddings.
The embeddings have to be in a broadcastable shape.
- Parameters
h (
FloatTensor
) – shape: (batch_size, num_entities, d_e) Head embeddings.r (
FloatTensor
) – shape: (batch_size, num_entities, d_r) Relation embeddings.t (
FloatTensor
) – shape: (batch_size, num_entities, d_e) Tail embeddings.m_r (
FloatTensor
) – shape: (batch_size, num_entities, d_e, d_r) The relation specific linear transformations.
- Return type
FloatTensor
- Returns
shape: (batch_size, num_entities) The scores.
-
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.