SGConvΒΆ
-
class
dgl.nn.pytorch.conv.
SGConv
(in_feats, out_feats, k=1, cached=False, bias=True, norm=None, allow_zero_in_degree=False)[source]ΒΆ Bases:
torch.nn.modules.module.Module
SGC layer from Simplifying Graph Convolutional Networks
\[H^{K} = (\tilde{D}^{-1/2} \tilde{A} \tilde{D}^{-1/2})^K X \Theta\]where \(\tilde{A}\) is \(A\) + \(I\). Thus the graph input is expected to have self-loop edges added.
- Parameters
in_feats (int) β Number of input features; i.e, the number of dimensions of \(X\).
out_feats (int) β Number of output features; i.e, the number of dimensions of \(H^{K}\).
k (int) β Number of hops \(K\). Defaults:
1
.cached (bool) β
If True, the module would cache
\[(\tilde{D}^{-\frac{1}{2}}\tilde{A}\tilde{D}^{-\frac{1}{2}})^K X\Theta\]at the first forward call. This parameter should only be set to
True
in Transductive Learning setting.bias (bool) β If True, adds a learnable bias to the output. Default:
True
.norm (callable activation function/layer or None, optional) β If not None, applies normalization to the updated node features. Default:
False
.allow_zero_in_degree (bool, optional) β 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. Setallow_zero_in_degree
toTrue
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>)
-
forward
(graph, feat, edge_weight=None)[source]ΒΆ Compute Simplifying Graph Convolution layer.
- Parameters
graph (DGLGraph) β The graph.
feat (torch.Tensor) β The input feature of shape \((N, D_{in})\) where \(D_{in}\) is size of input feature, \(N\) is the number of nodes.
edge_weight (torch.Tensor, optional) β edge_weight to use in the message passing process. This is equivalent to using weighted adjacency matrix in the equation above, and \(\tilde{D}^{-1/2}\tilde{A} \tilde{D}^{-1/2}\) is based on
dgl.nn.pytorch.conv.graphconv.EdgeWeightNorm
.
- Returns
The output feature of shape \((N, D_{out})\) where \(D_{out}\) is size of output feature.
- Return type
torch.Tensor
- Raises
DGLError β 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 toTrue
.
Note
If
cache
is set to True,feat
andgraph
should not change during training, or you will get wrong results.