torch_geometric_signed_directed.nn.general.MSConv
=================================================

.. py:module:: torch_geometric_signed_directed.nn.general.MSConv


Classes
-------

.. autoapisummary::

   torch_geometric_signed_directed.nn.general.MSConv.MSConv


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

.. py:class:: MSConv(in_channels: int, out_channels: int, K: int, q: float, trainable_q: bool, normalization: str = 'sym', bias: bool = True, cached: bool = False, absolute_degree: bool = True, **kwargs)

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


   Magnetic Signed Laplacian Convolution Layer from the
   `MSGNN: A Spectral Graph Neural Network Based on a Novel Magnetic Signed Laplacian <https://proceedings.mlr.press/v198/he22c.html>`_ paper.

   :Parameters: * **in_channels** (*int*) -- Size of each input sample.
                * **out_channels** (*int*) -- Size of each output sample.
                * **K** (*int*) -- Order of the Chebyshev polynomial, i.e., Chebyshev filter size minus 1 :math:`K`.
                * **q** (*float, optional*) -- Initial value of the phase parameter, 0 <= q <= 0.25. Default: 0.25.
                * **trainable_q** (*bool, optional*) -- whether to set q to be trainable or not. (default: :obj:`False`)
                * **normalization** (*str, optional*) -- The normalization scheme for the magnetic
                  Laplacian (default: :obj:`sym`):
                  1. :obj:`None`: No normalization
                  :math:`\mathbf{L} = \bar{\mathbf{D}} - \mathbf{A} \odot \exp(i \Theta^{(q)})`
                  2. :obj:`"sym"`: Symmetric normalization
                  :math:`\mathbf{L} = \mathbf{I} - \bar{\mathbf{D}}^{-1/2} \mathbf{A}
                  \bar{\mathbf{D}}^{-1/2} \odot \exp(i \Theta^{(q)})`
                  `\odot` denotes the element-wise multiplication.
                * **cached** (*bool, optional*) -- If set to :obj:`True`, the layer will cache
                  the __norm__ matrix on first execution, and will use the
                  cached version for further executions.
                  This parameter should only be set to :obj:`True` in transductive
                  learning scenarios. (default: :obj:`False`)
                * **bias** (*bool, optional*) -- If set to :obj:`False`, the layer will not learn
                  an additive bias. (default: :obj:`True`)
                * **absolute_degree** (*bool, optional*) -- Whether to calculate the degree matrix with respect to absolute entries of the adjacency matrix. (default: :obj:`True`)
                * **\*\*kwargs** (*optional*) -- Additional arguments of
                  :class:`torch_geometric.nn.conv.MessagePassing`.


   .. py:attribute:: in_channels


   .. py:attribute:: out_channels


   .. py:attribute:: normalization
      :value: 'sym'



   .. py:attribute:: cached
      :value: False



   .. py:attribute:: trainable_q


   .. py:attribute:: absolute_degree
      :value: True



   .. py:attribute:: weight


   .. py:method:: reset_parameters()


   .. py:method:: forward(x_real: torch.FloatTensor, x_imag: torch.FloatTensor, edge_index: torch.LongTensor, edge_weight: torch_geometric.typing.OptTensor = None, lambda_max: torch_geometric.typing.OptTensor = None) -> torch.FloatTensor

      Making a forward pass of the Signed Directed Magnetic Laplacian Convolution layer.

      Arg types:
          * x_real, x_imag (PyTorch Float Tensor) - Node features.
          * edge_index (PyTorch Long Tensor) - Edge indices.
          * edge_weight (PyTorch Float Tensor, optional) - Edge weights corresponding to edge indices.
          * lambda_max (optional, but mandatory if normalization is None) - Largest eigenvalue of Laplacian.
      Return types:
          * out_real, out_imag (PyTorch Float Tensor) - Hidden state tensor for all nodes, with shape (N_nodes, F_out).



   .. py:method:: message(x_j, norm)