NTNInteraction

class NTNInteraction(non_linearity=None)[source]

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

A stateful module for the NTN interaction function.

See also

pykeen.nn.functional.ntn_interaction()

Initializes internal Module state, shared by both nn.Module and ScriptModule.

Attributes Summary

relation_shape

The symbolic shapes for relation representations

Methods Summary

func(t, w, vh, vt, b, u, activation)

Evaluate the NTN interaction function.

Attributes Documentation

relation_shape: Sequence[str] = ('kdd', 'kd', 'kd', 'k', 'k')

The symbolic shapes for relation representations

Methods Documentation

func(t, w, vh, vt, b, u, activation)

Evaluate the NTN interaction function.

\[f(h,r,t) = u_r^T act(h W_r t + V_r h + V_r' t + b_r)\]
Parameters

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

  • w (FloatTensor) – shape: (batch_size, 1, num_relations, 1, k, dim, dim) The relation specific transformation matrix W_r.

  • vh (FloatTensor) – shape: (batch_size, 1, num_relations, 1, k, dim) The head transformation matrix V_h.

  • vt (FloatTensor) – shape: (batch_size, 1, num_relations, 1, k, dim) The tail transformation matrix V_h.

  • b (FloatTensor) – shape: (batch_size, 1, num_relations, 1, k) The relation specific offset b_r.

  • u (FloatTensor) – shape: (batch_size, 1, num_relations, 1, k) The relation specific final linear transformation b_r.

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

  • activation (Module) – The activation function.

Return type

FloatTensor

Returns

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