GINConv

class dgl.nn.pytorch.conv.GINConv(apply_func=None, aggregator_type='sum', init_eps=0, learn_eps=False, activation=None)[source]

Bases: Module

图同构网络层来自图神经网络有多强大？

\[h_i^{(l+1)} = f_\Theta \left((1 + \epsilon) h_i^{l} + \mathrm{aggregate}\left(\left\{h_j^{l}, j\in\mathcal{N}(i) \right\}\right)\right)\]

如果提供了每条边上的权重张量，加权图卷积定义为：

\[h_i^{(l+1)} = f_\Theta \left((1 + \epsilon) h_i^{l} + \mathrm{aggregate}\left(\left\{e_{ji} h_j^{l}, j\in\mathcal{N}(i) \right\}\right)\right)\]

其中 \(e_{ji}\) 是从节点 \(j\) 到节点 \(i\) 的边的权重。请确保 e_{ji} 与 h_j^{l} 是可广播的。

Parameters:

apply_func (可调用的激活函数/层 或 None) – 如果不为None，将此函数应用于更新后的节点特征，公式中的 \(f_\Theta\)，默认值：None。
aggregator_type (str) – 使用的聚合器类型 (sum, max 或 mean), 默认: ‘sum’.
init_eps (float, optional) – Initial \(\epsilon\) value, default: 0.
learn_eps (bool, optional) – If True, \(\epsilon\) will be a learnable parameter. Default: False.
activation (callable activation function/layer or None, optional) – If not None, applies an activation function to the updated node features. Default: None.

示例

>>> import dgl
>>> import numpy as np
>>> import torch as th
>>> from dgl.nn import GINConv
>>>
>>> g = dgl.graph(([0,1,2,3,2,5], [1,2,3,4,0,3]))
>>> feat = th.ones(6, 10)
>>> lin = th.nn.Linear(10, 10)
>>> conv = GINConv(lin, 'max')
>>> res = conv(g, feat)
>>> res
tensor([[-0.4821,  0.0207, -0.7665,  0.5721, -0.4682, -0.2134, -0.5236,  1.2855,
        0.8843, -0.8764],
        [-0.4821,  0.0207, -0.7665,  0.5721, -0.4682, -0.2134, -0.5236,  1.2855,
        0.8843, -0.8764],
        [-0.4821,  0.0207, -0.7665,  0.5721, -0.4682, -0.2134, -0.5236,  1.2855,
        0.8843, -0.8764],
        [-0.4821,  0.0207, -0.7665,  0.5721, -0.4682, -0.2134, -0.5236,  1.2855,
        0.8843, -0.8764],
        [-0.4821,  0.0207, -0.7665,  0.5721, -0.4682, -0.2134, -0.5236,  1.2855,
        0.8843, -0.8764],
        [-0.1804,  0.0758, -0.5159,  0.3569, -0.1408, -0.1395, -0.2387,  0.7773,
        0.5266, -0.4465]], grad_fn=<AddmmBackward>)

>>> # With activation
>>> from torch.nn.functional import relu
>>> conv = GINConv(lin, 'max', activation=relu)
>>> res = conv(g, feat)
>>> res
tensor([[5.0118, 0.0000, 0.0000, 3.9091, 1.3371, 0.0000, 0.0000, 0.0000, 0.0000,
         0.0000],
        [5.0118, 0.0000, 0.0000, 3.9091, 1.3371, 0.0000, 0.0000, 0.0000, 0.0000,
         0.0000],
        [5.0118, 0.0000, 0.0000, 3.9091, 1.3371, 0.0000, 0.0000, 0.0000, 0.0000,
         0.0000],
        [5.0118, 0.0000, 0.0000, 3.9091, 1.3371, 0.0000, 0.0000, 0.0000, 0.0000,
         0.0000],
        [5.0118, 0.0000, 0.0000, 3.9091, 1.3371, 0.0000, 0.0000, 0.0000, 0.0000,
         0.0000],
        [2.5011, 0.0000, 0.0089, 2.0541, 0.8262, 0.0000, 0.0000, 0.1371, 0.0000,
         0.0000]], grad_fn=<ReluBackward0>)

forward(graph, feat, edge_weight=None)[source]

Description

计算图同构网络层。

param graph:: 图表。
type graph:: DGLGraph
param feat:: 如果给定一个torch.Tensor，输入特征的形状为\((N, D_{in})\)，其中 \(D_{in}\)是输入特征的大小，\(N\)是节点的数量。如果给定一对torch.Tensor，这对张量必须包含两个形状为 \((N_{in}, D_{in})\)和\((N_{out}, D_{in})\)的张量。如果apply_func不为None，\(D_{in}\)应该符合apply_func的输入维度要求。
type feat:: torch.Tensor 或一对 torch.Tensor
param edge_weight:: 边缘上的可选张量。如果提供，卷积将根据消息进行加权。
type edge_weight:: torch.Tensor, 可选的
returns:: 输出特征的形状为 \((N, D_{out})\)，其中 \(D_{out}\) 是 apply_func 的输出维度。如果 apply_func 为 None，\(D_{out}\) 应与输入维度相同。
rtype:: torch.Tensor