class TuckerInteraction(embedding_dim=200, relation_dim=None, head_dropout=0.3, relation_dropout=0.4, head_relation_dropout=0.5, apply_batch_normalization=True)[source]

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

A stateful module for the stateless Tucker interaction function.

Initialize the Tucker interaction function.

  • embedding_dim (int) – The entity embedding dimension.

  • relation_dim (Optional[int]) – The relation embedding dimension.

  • head_dropout (float) – The dropout rate applied to the head representations.

  • relation_dropout (float) – The dropout rate applied to the relation representations.

  • head_relation_dropout (float) – The dropout rate applied to the combined head and relation representations.

  • apply_batch_normalization (bool) – Whether to use batch normalization on head representations and the combination of head and relation.

Methods Summary

func(r, t, core_tensor, do_h, do_r, do_hr, …)

Evaluate the TuckEr interaction function.


Reset parameters the interaction function may have.

Methods Documentation

func(r, t, core_tensor, do_h, do_r, do_hr, bn_h, bn_hr)

Evaluate the TuckEr interaction function.

Compute scoring function W x_1 h x_2 r x_3 t as in the official implementation, i.e. as

\[DO_{hr}(BN_{hr}(DO_h(BN_h(h)) x_1 DO_r(W x_2 r))) x_3 t\]

where BN denotes BatchNorm and DO denotes Dropout

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

  • r (FloatTensor) – shape: (batch_size, 1, num_relations, 1, d_r) The relation representations.

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

  • core_tensor (FloatTensor) – shape: (d_e, d_r, d_e) The core tensor.

  • do_h (Dropout) – The dropout layer for the head representations.

  • do_r (Dropout) – The first hidden dropout.

  • do_hr (Dropout) – The second hidden dropout.

  • bn_h (Optional[BatchNorm1d]) – The first batch normalization layer.

  • bn_hr (Optional[BatchNorm1d]) – The second batch normalization layer.

Return type



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


Reset parameters the interaction function may have.