APPNPConv

class dgl.nn.pytorch.conv.APPNPConv(k, alpha, edge_drop=0.0)[source]

Bases: Module

近似个性化神经预测传播层来自预测然后传播：图神经网络与个性化PageRank的结合

\[ \begin{align}\begin{aligned}H^{0} &= X\\H^{l+1} &= (1-\alpha)\left(\tilde{D}^{-1/2} \tilde{A} \tilde{D}^{-1/2} H^{l}\right) + \alpha H^{0}\end{aligned}\end{align} \]

其中 \(\tilde{A}\) 是 \(A\) + \(I\)。

Parameters:

k (int) – 迭代次数 \(K\)。
alpha (float) – 传送概率 \(\alpha\)。
edge_drop (float, 可选) – 控制每个节点接收到的消息的边缘丢弃率。默认值：0。

示例

>>> import dgl
>>> import numpy as np
>>> import torch as th
>>> from dgl.nn import APPNPConv
>>>
>>> g = dgl.graph(([0,1,2,3,2,5], [1,2,3,4,0,3]))
>>> feat = th.ones(6, 10)
>>> conv = APPNPConv(k=3, alpha=0.5)
>>> res = conv(g, feat)
>>> print(res)
tensor([[0.8536, 0.8536, 0.8536, 0.8536, 0.8536, 0.8536, 0.8536, 0.8536, 0.8536,
        0.8536],
        [0.9268, 0.9268, 0.9268, 0.9268, 0.9268, 0.9268, 0.9268, 0.9268, 0.9268,
        0.9268],
        [0.9634, 0.9634, 0.9634, 0.9634, 0.9634, 0.9634, 0.9634, 0.9634, 0.9634,
        0.9634],
        [0.9268, 0.9268, 0.9268, 0.9268, 0.9268, 0.9268, 0.9268, 0.9268, 0.9268,
        0.9268],
        [0.9634, 0.9634, 0.9634, 0.9634, 0.9634, 0.9634, 0.9634, 0.9634, 0.9634,
        0.9634],
        [0.5000, 0.5000, 0.5000, 0.5000, 0.5000, 0.5000, 0.5000, 0.5000, 0.5000,
        0.5000]])

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

Description

计算APPNP层。

param graph:: 图表。
type graph:: DGLGraph
param feat:: 输入特征的形状为 \((N, *)\)。\(N\) 是节点的数量，\(*\) 可以是任何形状。
type feat:: torch.Tensor
param edge_weight:: 在消息传递过程中使用的edge_weight。这相当于在上述方程中使用加权邻接矩阵，并且 \(\tilde{D}^{-1/2}\tilde{A} \tilde{D}^{-1/2}\) 是基于dgl.nn.pytorch.conv.graphconv.EdgeWeightNorm。
type edge_weight:: torch.Tensor, 可选
returns:: The output feature of shape \((N, *)\) where \(*\) should be the same as input shape.
rtype:: torch.Tensor