torch_geometric_signed_directed.nn.signed.SDGNN
===============================================

.. py:module:: torch_geometric_signed_directed.nn.signed.SDGNN


Classes
-------

.. autoapisummary::

   torch_geometric_signed_directed.nn.signed.SDGNN.SDRLayer
   torch_geometric_signed_directed.nn.signed.SDGNN.SDGNN


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

.. py:class:: SDRLayer(in_dim: int = 20, out_dim: int = 20, edge_lists: list = [], **kwargs)

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


   The signed directed relationship layer from
   `"SDGNN: Learning Node Representation for Signed Directed Networks" <https://arxiv.org/abs/2101.02390>`_ paper.

       Args:
           in_dim (int): Dimenson of input features. Defaults to 20.
           out_dim (int): Dimenson of output features. Defaults to 20.
           edge_lists (list): Edgelist for current motifs.


   .. py:attribute:: edge_lists
      :value: []



   .. py:attribute:: aggs
      :value: []



   .. py:attribute:: mlp_layer


   .. py:method:: reset_parameters()


   .. py:method:: forward(x: torch.FloatTensor) -> torch.FloatTensor


.. py:class:: SDGNN(node_num: int, edge_index_s, in_dim: int = 20, out_dim: int = 20, layer_num: int = 2, init_emb: torch.FloatTensor = None, init_emb_grad: bool = True, lamb_d: float = 5.0, lamb_t: float = 1.0, **kwargs)

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


   The SDGNN model from  `"SDGNN: Learning Node Representation for Signed Directed Networks" <https://arxiv.org/abs/2101.02390>`_ paper.

   :Parameters: * **node_num** (*int, optional*) -- The number of nodes.
                * **edge_index_s** (*LongTensor*) -- The edgelist with sign. (e.g., :obj:`torch.LongTensor([[0, 1, -1], [0, 2, 1]])` )
                * **in_dim** (*int, optional*) -- Size of each input sample features. Defaults to 20.
                * **out_dim** (*int*) -- Size of each hidden embeddings. Defaults to 20.
                * **layer_num** (*int, optional*) -- Number of layers. Defaults to 2.
                * **init_emb** -- (FloatTensor, optional): The initial embeddings. Defaults to :obj:`None`, which will use TSVD as initial embeddings.
                * **init_emb_grad** (*bool optional*) -- Whether to set the initial embeddings to be trainable. (default: :obj:`False`)
                * **lamb_d** (*float, optional*) -- Balances the direction loss contributions of the overall objective. (default: :obj:`1.0`)
                * **lamb_t** (*float, optional*) -- Balances the triangle loss contributions of the overall objective. (default: :obj:`1.0`)


   .. py:attribute:: node_num


   .. py:attribute:: in_dim
      :value: 20



   .. py:attribute:: out_dim
      :value: 20



   .. py:attribute:: layer_num
      :value: 2



   .. py:attribute:: device


   .. py:attribute:: lamb_d
      :value: 5.0



   .. py:attribute:: lamb_t
      :value: 1.0



   .. py:attribute:: pos_edge_index


   .. py:attribute:: neg_edge_index


   .. py:attribute:: x


   .. py:attribute:: adj_lists


   .. py:attribute:: edge_lists


   .. py:attribute:: layers
      :value: []



   .. py:attribute:: loss_sign


   .. py:attribute:: loss_direction


   .. py:attribute:: loss_tri


   .. py:method:: reset_parameters()


   .. py:method:: map_adj_to_edges(adj_list: List) -> torch.LongTensor


   .. py:method:: get_features(u: int, v: int, r_edgelists: List) -> Tuple[int, int, int, int, int, int, int, int, int, int, int, int, int, int, int, int]


   .. py:method:: build_adj_lists(edge_index_s: torch.LongTensor) -> List


   .. py:method:: forward() -> torch.FloatTensor


   .. py:method:: loss()