DGL：GraphConv

$$h_i^{(l+1)}=\sigma (b^{(l)}+\sum _{j\in \mathcal{N}(i)}\frac{1}{c_{ji}}{h}_j^{(l)}{W}^{(l)})$$

class GraphConv(nn.Module):
    def __init__(
        self,
        in_feats,
        out_feats,
        norm="both",
        weight=True,
        bias=True,
        activation=None,
        allow_zero_in_degree=False,
    ):
        super(GraphConv, self).__init__()
        if norm not in ("none", "both", "right", "left"):
            raise DGLError(
                'Invalid norm value. Must be either "none", "both", "right" or "left".'
                ' But got "{}".'.format(norm)
            )
        self._in_feats = in_feats
        self._out_feats = out_feats
        self._norm = norm
        self._allow_zero_in_degree = allow_zero_in_degree

        if weight:
            self.weight = nn.Parameter(th.Tensor(in_feats, out_feats))
        else:
            self.register_parameter("weight", None)

        if bias:
            self.bias = nn.Parameter(th.Tensor(out_feats))
        else:
            self.register_parameter("bias", None)

        self.reset_parameters()

        self._activation = activation

[docs]    def reset_parameters(self):
        r"""

        Description
        -----------
        Reinitialize learnable parameters.

        Note
        ----
        The model parameters are initialized as in the
        `original implementation <https://github.com/tkipf/gcn/blob/master/gcn/layers.py>`__
        where the weight :math:`W^{(l)}` is initialized using Glorot uniform initialization
        and the bias is initialized to be zero.

        """
        if self.weight is not None:
            init.xavier_uniform_(self.weight)
        if self.bias is not None:
            init.zeros_(self.bias)


    def set_allow_zero_in_degree(self, set_value):
        r"""

        Description
        -----------
        Set allow_zero_in_degree flag.

        Parameters
        ----------
        set_value : bool
            The value to be set to the flag.
        """
        self._allow_zero_in_degree = set_value

[docs]    def forward(self, graph, feat, weight=None, edge_weight=None):
        r"""

        Description
        -----------
        Compute graph convolution.

        Parameters
        ----------
        graph : DGLGraph
            The graph.
        feat : torch.Tensor or pair of torch.Tensor
            If a torch.Tensor is given, it represents the input feature of shape
            :math:`(N, D_{in})`
            where :math:`D_{in}` is size of input feature, :math:`N` is the number of nodes.
            If a pair of torch.Tensor is given, which is the case for bipartite graph, the pair
            must contain two tensors of shape :math:`(N_{in}, D_{in_{src}})` and
            :math:`(N_{out}, D_{in_{dst}})`.
        weight : torch.Tensor, optional
            Optional external weight tensor.
        edge_weight : torch.Tensor, optional
            Optional tensor on the edge. If given, the convolution will weight
            with regard to the message.

        Returns
        -------
        torch.Tensor
            The output feature

        Raises
        ------
        DGLError
            Case 1:
            If there are 0-in-degree nodes in the input graph, it will raise DGLError
            since no message will be passed to those nodes. This will cause invalid output.
            The error can be ignored by setting ``allow_zero_in_degree`` parameter to ``True``.

            Case 2:
            External weight is provided while at the same time the module
            has defined its own weight parameter.

        Note
        ----
        * Input shape: :math:`(N, *, \text{in_feats})` where * means any number of additional
          dimensions, :math:`N` is the number of nodes.
        * Output shape: :math:`(N, *, \text{out_feats})` where all but the last dimension are
          the same shape as the input.
        * Weight shape: :math:`(\text{in_feats}, \text{out_feats})`.
        """
        with graph.local_scope():
            if not self._allow_zero_in_degree:
                if (graph.in_degrees() == 0).any():
                    raise DGLError(
                        "There are 0-in-degree nodes in the graph, "
                        "output for those nodes will be invalid. "
                        "This is harmful for some applications, "
                        "causing silent performance regression. "
                        "Adding self-loop on the input graph by "
                        "calling `g = dgl.add_self_loop(g)` will resolve "
                        "the issue. Setting ``allow_zero_in_degree`` "
                        "to be `True` when constructing this module will "
                        "suppress the check and let the code run."
                    )
            aggregate_fn = fn.copy_u("h", "m")
            if edge_weight is not None:
                assert edge_weight.shape[0] == graph.num_edges()
                graph.edata["_edge_weight"] = edge_weight
                aggregate_fn = fn.u_mul_e("h", "_edge_weight", "m")

            # (BarclayII) For RGCN on heterogeneous graphs we need to support GCN on bipartite.
            feat_src, feat_dst = expand_as_pair(feat, graph)
            if self._norm in ["left", "both"]:
                degs = graph.out_degrees().to(feat_src).clamp(min=1)
                if self._norm == "both":
                    norm = th.pow(degs, -0.5)
                else:
                    norm = 1.0 / degs
                shp = norm.shape + (1,) * (feat_src.dim() - 1)
                norm = th.reshape(norm, shp)
                feat_src = feat_src * norm

            if weight is not None:
                if self.weight is not None:
                    raise DGLError(
                        "External weight is provided while at the same time the"
                        " module has defined its own weight parameter. Please"
                        " create the module with flag weight=False."
                    )
            else:
                weight = self.weight

            if self._in_feats > self._out_feats:
                # mult W first to reduce the feature size for aggregation.
                if weight is not None:
                    feat_src = th.matmul(feat_src, weight)
                graph.srcdata["h"] = feat_src
                graph.update_all(aggregate_fn, fn.sum(msg="m", out="h"))
                rst = graph.dstdata["h"]
            else:
                # aggregate first then mult W
                graph.srcdata["h"] = feat_src
                graph.update_all(aggregate_fn, fn.sum(msg="m", out="h"))
                rst = graph.dstdata["h"]
                if weight is not None:
                    rst = th.matmul(rst, weight)

            if self._norm in ["right", "both"]:
                degs = graph.in_degrees().to(feat_dst).clamp(min=1)
                if self._norm == "both":
                    norm = th.pow(degs, -0.5)
                else:
                    norm = 1.0 / degs
                shp = norm.shape + (1,) * (feat_dst.dim() - 1)
                norm = th.reshape(norm, shp)
                rst = rst * norm

            if self.bias is not None:
                rst = rst + self.bias

            if self._activation is not None:
                rst = self._activation(rst)

            return rst


    def extra_repr(self):
        """Set the extra representation of the module,
        which will come into effect when printing the model.
        """
        summary = "in={_in_feats}, out={_out_feats}"
        summary += ", normalization={_norm}"
        if "_activation" in self.__dict__:
            summary += ", activation={_activation}"
        return summary.format(**self.__dict__)