torch_geometric_signed_directed.nn.signed.SGCN
==============================================

.. py:module:: torch_geometric_signed_directed.nn.signed.SGCN


Classes
-------

.. autoapisummary::

   torch_geometric_signed_directed.nn.signed.SGCN.SGCN


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

.. py:class:: SGCN(node_num: int, edge_index_s: torch.LongTensor, in_dim: int = 64, out_dim: int = 64, layer_num: int = 2, init_emb: torch.FloatTensor = None, init_emb_grad: bool = False, lamb: float = 5, norm_emb: bool = False, **kwargs)

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


   The signed graph convolutional network model from the `"Signed Graph
   Convolutional Network" <https://arxiv.org/abs/1808.06354>`_ paper.
   Internally, the first part of this module uses the
   :class:`torch_geometric.nn.conv.SignedConv` operator.
   We have made some modifications to the original model :class:`torch_geometric.nn.SignedGCN` for the uniformity of model inputs.

   :Parameters: * **node_num** (*int*) -- The number of nodes.
                * **edge_index_s** (*LongTensor*) -- The edgelist with sign. (e.g., torch.LongTensor([[0, 1, -1], [0, 2, 1]]) )
                * **in_dim** (*int, optional*) -- Size of each input sample features. Defaults to 64.
                * **out_dim** (*int, optional*) -- Size of each output embeddings. Defaults to 64.
                * **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** (*float, optional*) -- Balances the contributions of the overall
                  objective. (default: :obj:`5`)
                * **norm_emb** (*bool, optional*) -- Whether to normalize embeddings. (default: :obj:`False`)


   .. py:attribute:: node_num


   .. py:attribute:: in_dim
      :value: 64



   .. py:attribute:: out_dim
      :value: 64



   .. py:attribute:: lamb
      :value: 5



   .. py:attribute:: device


   .. py:attribute:: pos_edge_index


   .. py:attribute:: neg_edge_index


   .. py:attribute:: x


   .. py:attribute:: conv1


   .. py:attribute:: convs


   .. py:attribute:: lsp_loss


   .. py:attribute:: structure_loss


   .. py:method:: reset_parameters()


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


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