ontolearn.nces_modules
======================

.. py:module:: ontolearn.nces_modules

.. autoapi-nested-parse::

   NCES modules.



Classes
-------

.. autoapisummary::

   ontolearn.nces_modules.MAB
   ontolearn.nces_modules.SAB
   ontolearn.nces_modules.ISAB
   ontolearn.nces_modules.PMA
   ontolearn.nces_modules.ConEx


Module Contents
---------------

.. py:class:: MAB(dim_Q, dim_K, dim_V, num_heads, ln=False)

   Bases: :py:obj:`torch.nn.Module`


   MAB module.


   .. py:attribute:: dim_V


   .. py:attribute:: num_heads


   .. py:attribute:: fc_q


   .. py:attribute:: fc_k


   .. py:attribute:: fc_v


   .. py:attribute:: fc_o


   .. py:method:: forward(Q, K)


.. py:class:: SAB(dim_in, dim_out, num_heads, ln=False)

   Bases: :py:obj:`torch.nn.Module`


   SAB module.


   .. py:attribute:: mab


   .. py:method:: forward(X)


.. py:class:: ISAB(dim_in, dim_out, num_heads, m, ln=False)

   Bases: :py:obj:`torch.nn.Module`


   ISAB module.


   .. py:attribute:: I


   .. py:attribute:: mab0


   .. py:attribute:: mab1


   .. py:method:: forward(X)


.. py:class:: PMA(dim, num_heads, num_seeds, ln=False)

   Bases: :py:obj:`torch.nn.Module`


   PMA module.


   .. py:attribute:: S


   .. py:attribute:: mab


   .. py:method:: forward(X)


.. py:class:: ConEx(embedding_dim, num_entities, num_relations, input_dropout, feature_map_dropout, kernel_size, num_of_output_channels)

   Bases: :py:obj:`torch.nn.Module`


   Convolutional Complex Knowledge Graph Embeddings


   .. py:attribute:: name
      :value: 'ConEx'



   .. py:attribute:: loss


   .. py:attribute:: embedding_dim


   .. py:attribute:: num_entities


   .. py:attribute:: num_relations


   .. py:attribute:: input_dropout


   .. py:attribute:: feature_map_dropout


   .. py:attribute:: kernel_size


   .. py:attribute:: num_of_output_channels


   .. py:attribute:: emb_ent_real


   .. py:attribute:: emb_ent_i


   .. py:attribute:: emb_rel_real


   .. py:attribute:: emb_rel_i


   .. py:attribute:: input_dp_ent_real


   .. py:attribute:: input_dp_ent_i


   .. py:attribute:: input_dp_rel_real


   .. py:attribute:: input_dp_rel_i


   .. py:attribute:: bn_ent_real


   .. py:attribute:: bn_ent_i


   .. py:attribute:: bn_rel_real


   .. py:attribute:: bn_rel_i


   .. py:attribute:: conv1


   .. py:attribute:: fc_num_input


   .. py:attribute:: fc


   .. py:attribute:: bn_conv1


   .. py:attribute:: bn_conv2


   .. py:attribute:: feature_dropout


   .. py:method:: residual_convolution(C_1, C_2)


   .. py:method:: forward_head_batch(*, e1_idx, rel_idx)

      Given a head entity and a relation (h,r), we compute scores for all entities.
      [score(h,r,x)|x \in Entities] => [0.0,0.1,...,0.8], shape=> (1, |Entities|)
      Given a batch of head entities and relations => shape (size of batch,| Entities|)



   .. py:method:: forward_head_and_loss(e1_idx, rel_idx, targets)


   .. py:method:: init()


   .. py:method:: get_embeddings()


   .. py:method:: forward_triples(*, e1_idx, rel_idx, e2_idx)


   .. py:method:: forward_triples_and_loss(e1_idx, rel_idx, e2_idx, targets)