ERMLPE

class ERMLPE(*, hidden_dim=300, input_dropout=0.2, hidden_dropout=0.3, embedding_dim=200, entity_initializer=<function uniform_>, relation_initializer=<function uniform_>, **kwargs)[source]

Bases: pykeen.models.base.EntityRelationEmbeddingModel

An extension of pykeen.models.ERMLP proposed by [sharifzadeh2019].

This model uses a neural network-based approach similar to ER-MLP and with slight modifications. In ER-MLP, the model is:

\[f(h, r, t) = \textbf{w}^{T} g(\textbf{W} [\textbf{h}; \textbf{r}; \textbf{t}])\]

whereas in ER-MPL (E) the model is:

\[f(h, r, t) = \textbf{t}^{T} f(\textbf{W} (g(\textbf{W} [\textbf{h}; \textbf{r}]))\]

including dropouts and batch-norms between each two hidden layers. ConvE can be seen as a special case of ER-MLP (E )that contains the unnecessary inductive bias of convolutional filters. The aim of this model is to show that lifting this bias from pykeen.models.ConvE (which simply leaves us with a modified ER-MLP model), not only reduces the number of parameters but also improves performance.

Initialize the entity embedding model.

See also

Constructor of the base class pykeen.models.Model

Attributes Summary

hpo_default

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

loss_default_kwargs

The default parameters for the default loss function class

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'>}, 'hidden_dim': {'high': 9, 'low': 5, 'scale': 'power_two', 'type': <class 'int'>}, 'hidden_dropout': {'high': 0.5, 'low': 0.0, 'q': 0.1, 'type': <class 'float'>}, 'input_dropout': {'high': 0.5, 'low': 0.0, 'q': 0.1, 'type': <class 'float'>}}

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

loss_default_kwargs: ClassVar[Mapping[str, Any]] = {}

The default parameters for the default loss function class

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.