PyTorch Geometric(PyG) torch_geometric.nn.conv.gcn_conv源码详解

这个类继承自MessagePassing也就是Convolutional Layers

import torch
from torch.nn import Parameter
from torch_scatter import scatter_add
from torch_geometric.nn.conv import MessagePassing
from torch_geometric.utils import add_remaining_self_loops

from ..inits import glorot, zeros


class GCNConv(MessagePassing):
    r"""The graph convolutional operator from the `"Semi-supervised
    Classification with Graph Convolutional Networks"
    <https://arxiv.org/abs/1609.02907>`_ paper

    .. math::
        \mathbf{X}^{\prime} = \mathbf{\hat{D}}^{-1/2} \mathbf{\hat{A}}
        \mathbf{\hat{D}}^{-1/2} \mathbf{X} \mathbf{\Theta},

    where :math:`\mathbf{\hat{A}} = \mathbf{A} + \mathbf{I}` denotes the
    adjacency matrix with inserted self-loops and
    :math:`\hat{D}_{ii} = \sum_{j=0} \hat{A}_{ij}` its diagonal degree matrix.

    Args:
        in_channels (int): Size of each input sample.
        out_channels (int): Size of each output sample.
        improved (bool, optional): If set to :obj:`True`, the layer computes
            :math:`\mathbf{\hat{A}}` as :math:`\mathbf{A} + 2\mathbf{I}`.
            (default: :obj:`False`)
        cached (bool, optional): If set to :obj:`True`, the layer will cache
            the computation of :math:`\mathbf{\hat{D}}^{-1/2} \mathbf{\hat{A}}
            \mathbf{\hat{D}}^{-1/2}` 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`)
        normalize (bool, optional): Whether to add self-loops and apply
            symmetric normalization. (default: :obj:`True`)
        **kwargs (optional): Additional arguments of
            :class:`torch_geometric.nn.conv.MessagePassing`.
    """

    def __init__(self, in_channels, out_channels, improved=False, cached=False,
                 bias=True, normalize=True, **kwargs):
        super(GCNConv, self).__init__(aggr='add', **kwargs)

        self.in_channels = in_channels#输入通道数，也就是X的shape[1]
        self.out_channels = out_channels#输出通道数
        self.improved = improved#$设置为true时A尖等于A+2I
      
        self.cached = cached#If set to True, the layer will cache the computation of D^−1/2A^D^−1/2 on first execution, and will use the cached version for further executions. This parameter should only be set to True in transductive learning scenarios. (default: False)
        self.normalize = normalize#是否添加自环并应用对称归一化。

        self.weight = Parameter(torch.Tensor(in_channels, out_channels))

        if bias:#如果设置为False，则该层将不会学习加法偏差
            self.bias = Parameter(torch.Tensor(out_channels))
        else:
            self.register_parameter('bias', None)

        self.reset_parameters()

    def reset_parameters(self):
        glorot(self.weight)#glorot函数下面有写，初始化weight矩阵
        zeros(self.bias)#zeros函数下面有写，初始化偏置矩阵
        self.cached_result = None
        self.cached_num_edges = None


    @staticmethod
    def norm(edge_index, num_nodes, edge_weight=None, improved=False,
             dtype=None):
        if edge_weight is None:
            edge_weight = torch.ones((edge_index.size(1), ), dtype=dtype,
                                     device=edge_index.device)

        fill_value = 1 if not improved else 2
        edge_index, edge_weight = add_remaining_self_loops(
            edge_index, edge_weight, fill_value, num_nodes)

        row, col = edge_index
        deg = scatter_add(edge_weight, row, dim=0, dim_size=num_nodes)
        deg_inv_sqrt = deg.pow(-0.5)
        deg_inv_sqrt[deg_inv_sqrt == float('inf')] = 0

        return edge_index, deg_inv_sqrt[row] * edge_weight * deg_inv_sqrt[col]


    def forward(self, x, edge_index, edge_weight=None):
        """"""
        x = torch.matmul(x, self.weight)#将x与权重矩阵相乘

        if self.cached and self.cached_result is not None:
            if edge_index.size(1) != self.cached_num_edges:
                raise RuntimeError(
                    'Cached {} number of edges, but found {}. Please '
                    'disable the caching behavior of this layer by removing '
                    'the `cached=True` argument in its constructor.'.format(
                        self.cached_num_edges, edge_index.size(1)))

        if not self.cached or self.cached_result is None:
            self.cached_num_edges = edge_index.size(1)
            if self.normalize:
                edge_index, norm = self.norm(edge_index, x.size(
                    self.node_dim), edge_weight, self.improved, x.dtype)
            else:
                norm = edge_weight
            self.cached_result = edge_index, norm

        edge_index, norm = self.cached_result

        return self.propagate(edge_index, x=x, norm=norm)


    def message(self, x_j, norm):
        return norm.view(-1, 1) * x_j if norm is not None else x_j

    def update(self, aggr_out):
        if self.bias is not None:
            aggr_out = aggr_out + self.bias
        return aggr_out

    def __repr__(self):
        return '{}({}, {})'.format(self.__class__.__name__, self.in_channels,
                                   self.out_channels)

def glorot(tensor):#inits.py中
    if tensor is not None:
        stdv = math.sqrt(6.0 / (tensor.size(-2) + tensor.size(-1)))
        tensor.data.uniform_(-stdv, stdv)#将tensor的值设置为-stdv, stdv之间
def zeros(tensor):
    if tensor is not None:
        tensor.data.fill_(0)

用到的原理公式：

持续更新