sageconv_updated.py

from typing import Union, Tuple
from torch_geometric.typing import OptPairTensor, Adj, Size

from torch import Tensor
import torch.nn.functional as F
from torch_sparse import SparseTensor, matmul
from torch_geometric.nn.conv import MessagePassing
from torch_geometric.nn.dense.linear import Linear


# Note: SAGEConv first performs aggregation and then applies linear transformation, which is not memory efficient for datasets with high-dimensional original features (like coauthor-physics). 
#     So we manually create SAGEConv_updated, which first applies linear transformation and then performs aggregation.

class Sage_conv(MessagePassing):
    r"""The GraphSAGE operator from the `"Inductive Representation Learning on
    Large Graphs" <https://arxiv.org/abs/1706.02216>`_ paper

    .. math::
        \mathbf{x}^{\prime}_i = \mathbf{W}_1 \mathbf{x}_i + \mathbf{W}_2 \cdot
        \mathrm{mean}_{j \in \mathcal{N(i)}} \mathbf{x}_j

    Args:
        in_channels (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_channels (int): Size of each output sample.
        normalize (bool, optional): If set to :obj:`True`, output features
            will be :math:`\ell_2`-normalized, *i.e.*,
            :math:`\frac{\mathbf{x}^{\prime}_i}
            {\| \mathbf{x}^{\prime}_i \|_2}`.
            (default: :obj:`False`)
        root_weight (bool, optional): If set to :obj:`False`, the layer will
            not add transformed root node features to the output.
            (default: :obj:`True`)
        bias (bool, optional): If set to :obj:`False`, the layer will not learn
            an additive bias. (default: :obj:`True`)
        **kwargs (optional): Additional arguments of
            :class:`torch_geometric.nn.conv.MessagePassing`.
    """
    def __init__(self, in_channels: Union[int, Tuple[int, int]],
                 out_channels: int, normalize: bool = False,
                 root_weight: bool = True,
                 bias: bool = True, **kwargs):  # yapf: disable
        kwargs.setdefault('aggr', 'mean')
        super(Sage_conv, self).__init__(**kwargs)

        self.in_channels = in_channels
        self.out_channels = out_channels
        self.normalize = normalize
        self.root_weight = root_weight

        if isinstance(in_channels, int):
            in_channels = (in_channels, in_channels)

        self.lin_l = Linear(in_channels[0], out_channels, bias=bias)
        if self.root_weight:
            self.lin_r = Linear(in_channels[1], out_channels, bias=False)

        self.reset_parameters()

    def reset_parameters(self):
        self.lin_l.reset_parameters()
        if self.root_weight:
            self.lin_r.reset_parameters()

    def forward(self, x: Union[Tensor, OptPairTensor], edge_index: Adj,
                size: Size = None) -> Tensor:
        """"""
        if isinstance(x, Tensor):
            x: OptPairTensor = (x, x)

        # propagate_type: (x: OptPairTensor)
        # out = self.propagate(edge_index, x=x, size=size)
        # out = self.lin_l(out)

        out = self.lin_l(x[0])
        out = self.propagate(edge_index, x=(out,out),size=size)

        x_r = x[1]
        if self.root_weight and x_r is not None:
            out += self.lin_r(x_r)

        if self.normalize:
            out = F.normalize(out, p=2., dim=-1)

        return out

    def message(self, x_j: Tensor) -> Tensor:
        return x_j

    def message_and_aggregate(self, adj_t: SparseTensor,
                              x: OptPairTensor) -> Tensor:
        adj_t = adj_t.set_value(None, layout=None)
        return matmul(adj_t, x[0], reduce=self.aggr)

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