TransRInteraction

class TransRInteraction(p, power_norm=True)[source]

Bases: NormBasedInteraction[FloatTensor, Tuple[FloatTensor, FloatTensor], FloatTensor]

A stateful module for the TransR interaction function.

See also

pykeen.nn.functional.transr_interaction()

Initialize the interaction module.

Parameters:

  • p (int) – the \(p\) value of the norm to use, cf. NormBasedInteraction.__init__()

  • power_norm (bool) – whether to use the \(p`th power of the p-norm, cf. :meth:`NormBasedInteraction.__init__\).

Attributes Summary

relation_shape

The symbolic shapes for relation representations

Methods Summary

func(r, t, m_r, p[, power_norm])

Evaluate the TransR interaction function.

Attributes Documentation

relation_shape: Sequence[str] = ('e', 'de')

The symbolic shapes for relation representations

Methods Documentation

func(r, t, m_r, p, power_norm=True)

Evaluate the TransR interaction function.

Parameters:

  • h (FloatTensor) – shape: (*batch_dims, d_e) Head embeddings.

  • r (FloatTensor) – shape: (*batch_dims, d_r) Relation embeddings.

  • m_r (FloatTensor) – shape: (*batch_dims, d_e, d_r) The relation specific linear transformations.

  • t (FloatTensor) – shape: (*batch_dims, d_e) Tail embeddings.

  • p (int) – The parameter p for selecting the norm.

  • power_norm (bool) – Whether to return the powered norm instead.

Return type:

FloatTensor

Returns:

shape: batch_dims The scores.