torch_geometric_signed_directed.nn.signed.SGCNConv
==================================================

.. py:module:: torch_geometric_signed_directed.nn.signed.SGCNConv


Classes
-------

.. autoapisummary::

   torch_geometric_signed_directed.nn.signed.SGCNConv.SGCNConv


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

.. py:class:: SGCNConv(in_dim: int, out_dim: int, first_aggr: bool, bias: bool = True, norm_emb: bool = False, **kwargs)

   Bases: :py:obj:`torch_geometric.nn.conv.MessagePassing`


   The signed graph convolutional operator from the `"Signed Graph
   Convolutional Network" <https://arxiv.org/abs/1808.06354>`_ paper

   .. math::
       \mathbf{x}_v^{(\textrm{pos})} &= \mathbf{\Theta}^{(\textrm{pos})}
       \left[ \frac{1}{|\mathcal{N}^{+}(v)|} \sum_{w \in \mathcal{N}^{+}(v)}
       \mathbf{x}_w , \mathbf{x}_v \right]

       \mathbf{x}_v^{(\textrm{neg})} &= \mathbf{\Theta}^{(\textrm{neg})}
       \left[ \frac{1}{|\mathcal{N}^{-}(v)|} \sum_{w \in \mathcal{N}^{-}(v)}
       \mathbf{x}_w , \mathbf{x}_v \right]

   if :obj:`first_aggr` is set to :obj:`True`, and

   .. math::
       \mathbf{x}_v^{(\textrm{pos})} &= \mathbf{\Theta}^{(\textrm{pos})}
       \left[ \frac{1}{|\mathcal{N}^{+}(v)|} \sum_{w \in \mathcal{N}^{+}(v)}
       \mathbf{x}_w^{(\textrm{pos})}, \frac{1}{|\mathcal{N}^{-}(v)|}
       \sum_{w \in \mathcal{N}^{-}(v)} \mathbf{x}_w^{(\textrm{neg})},
       \mathbf{x}_v^{(\textrm{pos})} \right]

       \mathbf{x}_v^{(\textrm{neg})} &= \mathbf{\Theta}^{(\textrm{pos})}
       \left[ \frac{1}{|\mathcal{N}^{+}(v)|} \sum_{w \in \mathcal{N}^{+}(v)}
       \mathbf{x}_w^{(\textrm{neg})}, \frac{1}{|\mathcal{N}^{-}(v)|}
       \sum_{w \in \mathcal{N}^{-}(v)} \mathbf{x}_w^{(\textrm{pos})},
       \mathbf{x}_v^{(\textrm{neg})} \right]

   otherwise.
   In case :obj:`first_aggr` is :obj:`False`, the layer expects :obj:`x` to be
   a tensor where :obj:`x[:, :in_dim]` denotes the positive node features
   :math:`\mathbf{X}^{(\textrm{pos})}` and :obj:`x[:, in_dim:]` denotes
   the negative node features :math:`\mathbf{X}^{(\textrm{neg})}`.

   :Parameters: * **in_dim** (*int or tuple*) -- Size of each input sample, or :obj:`-1` to
                  derive the size from the first input(s) to the forward method.
                  A tuple corresponds to the sizes of source and target
                  dimensionalities.
                * **out_dim** (*int*) -- Size of each output sample.
                * **first_aggr** (*bool*) -- Denotes which aggregation formula to use.
                * **norm_emb** (*bool, optional*) -- Whether to normalize embeddings. (default: :obj:`False`)
                * **bias** (*bool, optional*) -- If set to :obj:`False`, the layer will not learn
                  an additive bias. (default: :obj:`True`)
                * **norm_emb** (*bool*) -- Denotes embedding is normalized or not. (default: :obj:`False`)
                * **\*\*kwargs** (*optional*) -- Additional arguments of
                  :class:`torch_geometric.nn.conv.MessagePassing`.


   .. py:attribute:: in_dim


   .. py:attribute:: out_dim


   .. py:attribute:: first_aggr


   .. py:attribute:: norm_emb
      :value: False



   .. py:method:: reset_parameters()


   .. py:method:: forward(x: Union[torch.Tensor, torch_geometric.typing.PairTensor], pos_edge_index: torch_geometric.typing.Adj, neg_edge_index: torch_geometric.typing.Adj) -> torch.Tensor


   .. py:method:: message(x_j: torch.Tensor) -> torch.Tensor


   .. py:method:: message_and_aggregate(adj_t: torch_geometric.typing.SparseTensor, x: torch_geometric.typing.PairTensor) -> torch.Tensor