PairREInteraction

class PairREInteraction(p, power_norm=False)[source]

Bases: pykeen.nn.modules.TranslationalInteraction[torch.FloatTensor, Tuple[torch.FloatTensor, torch.FloatTensor], torch.FloatTensor]

A stateful module for the PairRE interaction function.

See also

pykeen.nn.functional.pair_re_interaction()

Initialize the translational interaction function.

Parameters

  • p (int) – The norm used with torch.norm(). Typically is 1 or 2.

  • power_norm (bool) – Whether to use the p-th power of the L_p norm. It has the advantage of being differentiable around 0, and numerically more stable.

Attributes Summary

relation_shape

The symbolic shapes for relation representations

Methods Summary

func(t, r_h, r_t[, p, power_norm])

Evaluate the PairRE interaction function.

Attributes Documentation

relation_shape: Sequence[str] = ('d', 'd')

The symbolic shapes for relation representations

Methods Documentation

func(t, r_h, r_t, p=2, power_norm=True)

Evaluate the PairRE interaction function.

\[-\|h \odot r_h - t \odot r_t \|\]
Parameters

  • h (FloatTensor) – shape: (batch_size, num_heads, 1, 1, dim) The head representations.

  • t (FloatTensor) – shape: (batch_size, 1, 1, num_tails, dim) The tail representations.

  • r_h (FloatTensor) – shape: (batch_size, 1, num_relations, 1, dim) The head part of the relation representations.

  • r_t (FloatTensor) – shape: (batch_size, 1, num_relations, 1, dim) The tail part of the relation representations.

  • p (Union[int, str]) – The parameter p for selecting the norm.

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

Return type

FloatTensor

Returns

shape: (batch_size, num_heads, num_relations, num_tails) The scores.