Source code for torch_geometric.nn.conv.sg_conv

from typing import Optional
from torch_geometric.typing import Adj, OptTensor

from torch import Tensor
from torch.nn import Linear
from torch_sparse import SparseTensor, matmul
from torch_geometric.nn.conv import MessagePassing
from torch_geometric.nn.conv.gcn_conv import gcn_norm


[docs]class SGConv(MessagePassing): r"""The simple graph convolutional operator from the `"Simplifying Graph Convolutional Networks" <https://arxiv.org/abs/1902.07153>`_ paper .. math:: \mathbf{X}^{\prime} = {\left(\mathbf{\hat{D}}^{-1/2} \mathbf{\hat{A}} \mathbf{\hat{D}}^{-1/2} \right)}^K \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. K (int, optional): Number of hops :math:`K`. (default: :obj:`1`) cached (bool, optional): If set to :obj:`True`, the layer will cache the computation of :math:`{\left(\mathbf{\hat{D}}^{-1/2} \mathbf{\hat{A}} \mathbf{\hat{D}}^{-1/2} \right)}^K \mathbf{X}` 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`) add_self_loops (bool, optional): If set to :obj:`False`, will not add self-loops to the input graph. (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`. """ _cached_x: Optional[Tensor] def __init__(self, in_channels: int, out_channels: int, K: int = 1, cached: bool = False, add_self_loops: bool = True, bias: bool = True, **kwargs): super(SGConv, self).__init__(aggr='add', **kwargs) self.in_channels = in_channels self.out_channels = out_channels self.K = K self.cached = cached self.add_self_loops = add_self_loops self._cached_x = None self.lin = Linear(in_channels, out_channels, bias=bias) self.reset_parameters()
[docs] def reset_parameters(self): self.lin.reset_parameters() self._cached_x = None
[docs] def forward(self, x: Tensor, edge_index: Adj, edge_weight: OptTensor = None) -> Tensor: """""" cache = self._cached_x if cache is None: if isinstance(edge_index, Tensor): edge_index, edge_weight = gcn_norm( # yapf: disable edge_index, edge_weight, x.size(self.node_dim), False, self.add_self_loops, dtype=x.dtype) elif isinstance(edge_index, SparseTensor): edge_index = gcn_norm( # yapf: disable edge_index, edge_weight, x.size(self.node_dim), False, self.add_self_loops, dtype=x.dtype) for k in range(self.K): # propagate_type: (x: Tensor, edge_weight: OptTensor) x = self.propagate(edge_index, x=x, edge_weight=edge_weight, size=None) if self.cached: self._cached_x = x else: x = cache return self.lin(x)
def message(self, x_j: Tensor, edge_weight: Tensor) -> Tensor: return edge_weight.view(-1, 1) * x_j def message_and_aggregate(self, adj_t: SparseTensor, x: Tensor) -> Tensor: return matmul(adj_t, x, reduce=self.aggr) def __repr__(self): return '{}({}, {}, K={})'.format(self.__class__.__name__, self.in_channels, self.out_channels, self.K)