Source code for dgl.nn.pytorch.conv.sgconv

"""Torch Module for Simplifying Graph Convolution layer"""
# pylint: disable= no-member, arguments-differ, invalid-name
import torch as th
from torch import nn

from .... import function as fn
from ....base import DGLError
from .graphconv import EdgeWeightNorm


[docs]class SGConv(nn.Module): r"""SGC layer from `Simplifying Graph Convolutional Networks <https://arxiv.org/pdf/1902.07153.pdf>`__ .. math:: H^{K} = (\tilde{D}^{-1/2} \tilde{A} \tilde{D}^{-1/2})^K X \Theta where :math:`\tilde{A}` is :math:`A` + :math:`I`. Thus the graph input is expected to have self-loop edges added. Parameters ---------- in_feats : int Number of input features; i.e, the number of dimensions of :math:`X`. out_feats : int Number of output features; i.e, the number of dimensions of :math:`H^{K}`. k : int Number of hops :math:`K`. Defaults:``1``. cached : bool If True, the module would cache .. math:: (\tilde{D}^{-\frac{1}{2}}\tilde{A}\tilde{D}^{-\frac{1}{2}})^K X\Theta at the first forward call. This parameter should only be set to ``True`` in Transductive Learning setting. bias : bool If True, adds a learnable bias to the output. Default: ``True``. norm : callable activation function/layer or None, optional If not None, applies normalization to the updated node features. Default: ``False``. allow_zero_in_degree : bool, optional If there are 0-in-degree nodes in the graph, output for those nodes will be invalid since no message will be passed to those nodes. This is harmful for some applications causing silent performance regression. This module will raise a DGLError if it detects 0-in-degree nodes in input graph. By setting ``True``, it will suppress the check and let the users handle it by themselves. Default: ``False``. Note ---- Zero in-degree nodes will lead to invalid output value. This is because no message will be passed to those nodes, the aggregation function will be appied on empty input. A common practice to avoid this is to add a self-loop for each node in the graph if it is homogeneous, which can be achieved by: >>> g = ... # a DGLGraph >>> g = dgl.add_self_loop(g) Calling ``add_self_loop`` will not work for some graphs, for example, heterogeneous graph since the edge type can not be decided for self_loop edges. Set ``allow_zero_in_degree`` to ``True`` for those cases to unblock the code and handle zero-in-degree nodes manually. A common practise to handle this is to filter out the nodes with zero-in-degree when use after conv. Example ------- >>> import dgl >>> import numpy as np >>> import torch as th >>> from dgl.nn import SGConv >>> >>> g = dgl.graph(([0,1,2,3,2,5], [1,2,3,4,0,3])) >>> g = dgl.add_self_loop(g) >>> feat = th.ones(6, 10) >>> conv = SGConv(10, 2, k=2) >>> res = conv(g, feat) >>> res tensor([[-1.9441, -0.9343], [-1.9441, -0.9343], [-1.9441, -0.9343], [-2.7709, -1.3316], [-1.9297, -0.9273], [-1.9441, -0.9343]], grad_fn=<AddmmBackward>) """ def __init__( self, in_feats, out_feats, k=1, cached=False, bias=True, norm=None, allow_zero_in_degree=False, ): super(SGConv, self).__init__() self.fc = nn.Linear(in_feats, out_feats, bias=bias) self._cached = cached self._cached_h = None self._k = k self.norm = norm self._allow_zero_in_degree = allow_zero_in_degree self.reset_parameters()
[docs] def reset_parameters(self): r""" Description ----------- Reinitialize learnable parameters. Note ---- The model parameters are initialized using xavier initialization and the bias is initialized to be zero. """ nn.init.xavier_uniform_(self.fc.weight) if self.fc.bias is not None: nn.init.zeros_(self.fc.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, edge_weight=None): r""" Description ----------- Compute Simplifying Graph Convolution layer. Parameters ---------- graph : DGLGraph The graph. feat : torch.Tensor 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. edge_weight: torch.Tensor, optional edge_weight to use in the message passing process. This is equivalent to using weighted adjacency matrix in the equation above, and :math:`\tilde{D}^{-1/2}\tilde{A} \tilde{D}^{-1/2}` is based on :class:`dgl.nn.pytorch.conv.graphconv.EdgeWeightNorm`. Returns ------- torch.Tensor The output feature of shape :math:`(N, D_{out})` where :math:`D_{out}` is size of output feature. Raises ------ DGLError 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``. Note ---- If ``cache`` is set to True, ``feat`` and ``graph`` should not change during training, or you will get wrong results. """ 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." ) msg_func = fn.copy_u("h", "m") if edge_weight is not None: graph.edata["_edge_weight"] = EdgeWeightNorm("both")( graph, edge_weight ) msg_func = fn.u_mul_e("h", "_edge_weight", "m") if self._cached_h is not None: feat = self._cached_h else: if edge_weight is None: # compute normalization degs = graph.in_degrees().to(feat).clamp(min=1) norm = th.pow(degs, -0.5) norm = norm.to(feat.device).unsqueeze(1) # compute (D^-1 A^k D)^k X for _ in range(self._k): if edge_weight is None: feat = feat * norm graph.ndata["h"] = feat graph.update_all(msg_func, fn.sum("m", "h")) feat = graph.ndata.pop("h") if edge_weight is None: feat = feat * norm if self.norm is not None: feat = self.norm(feat) # cache feature if self._cached: self._cached_h = feat return self.fc(feat)