论文解读(VGAE)《Variational Graph Auto-Encoders》
Paper Information
Title:Variational Graph Auto-Encoders
Authors:Thomas Kipf, M. Welling
Soures:2016, ArXiv
Others:1214 Citations, 14 References
1 A latent variable model for graph-structured data
VGAE 使用了一个 GCN encoder 和 一个简单的内积 decoder ,架构如下图所示:

Definitions:We are given an undirected, unweighted graph $\mathcal{G}=(\mathcal{V}, \mathcal{E})$ with $N=|\mathcal{V}|$ nodes. We introduce an adjacency matrix $\mathbf{A}$ of $\mathcal{G}$ (we assume diagonal elements set to $1$ , i.e. every node is connected to itself) and its degree matrix $\mathbf{D}$ . We further introduce stochastic latent variables $\mathbf{z}_{i}$ , summarized in an $N \times F$ matrix $\mathbf{Z}$ . Node features are summarized in an $N \times D$ matrix $\mathbf{X}$ .
Inference model:使用一个两层的 GCN 推理模型
$q(\mathbf{Z} \mid \mathbf{X}, \mathbf{A})=\prod_{i=1}^{N} q\left(\mathbf{z}_{i} \mid \mathbf{X}, \mathbf{A}\right) \text { with } \quad q\left(\mathbf{z}_{i} \mid \mathbf{X}, \mathbf{A}\right)=\mathcal{N}\left(\mathbf{z}_{i} \mid \boldsymbol{\mu}_{i}, \operatorname{diag}\left(\boldsymbol{\sigma}_{i}^{2}\right)\right)$
其中:
- $\boldsymbol{\mu}=\operatorname{GCN}_{\boldsymbol{\mu}}(\mathbf{X}, \mathbf{A})$ is the matrix of mean vectors $\boldsymbol{\mu}_{i} $;
- $\log \boldsymbol{\sigma}=\mathrm{GCN}_{\boldsymbol{\sigma}}(\mathbf{X}, \mathbf{A})$;
def encode(self, x, adj):
hidden1 = self.gc1(x, adj)
return self.gc2(hidden1, adj), self.gc3(hidden1, adj) mu, logvar = self.encode(x, adj)
GCN 的第二层分别输出 mu,log $\sigma$ 矩阵,共用第一层的参数。
这里 GCN 定义为:
$\operatorname{GCN}(\mathbf{X}, \mathbf{A})=\tilde{\mathbf{A}} \operatorname{ReLU}\left(\tilde{\mathbf{A}} \mathbf{X} \mathbf{W}_{0}\right) \mathbf{W}_{1}$
其中:
- $\mathbf{W}_{i}$ 代表着权重矩阵
- $\operatorname{GCN}_{\boldsymbol{\mu}}(\mathbf{X}, \mathbf{A})$ 和 $\mathrm{GCN}_{\boldsymbol{\sigma}}(\mathbf{X}, \mathbf{A})$ 共享第一层的权重矩阵 $\mathbf{W}_{0} $
- $\operatorname{ReLU}(\cdot)=\max (0, \cdot)$
- $\tilde{\mathbf{A}}=\mathbf{D}^{-\frac{1}{2}} \mathbf{A} \mathbf{D}^{-\frac{1}{2}}$ 代表着 symmetrically normalized adjacency matrix
至于 $z$ 的生成:
def reparameterize(self, mu, logvar):
if self.training:
std = torch.exp(logvar)
eps = torch.randn_like(std)
return eps.mul(std).add_(mu)
else:
return mu z = self.reparameterize(mu, logvar)
Generative model:我们的生成模型是由潜在变量之间的内积给出的:
$p(\mathbf{A} \mid \mathbf{Z})=\prod_{i=1}^{N} \prod_{j=1}^{N} p\left(A_{i j} \mid \mathbf{z}_{i}, \mathbf{z}_{j}\right) \text { with } p\left(A_{i j}=1 \mid \mathbf{z}_{i}, \mathbf{z}_{j}\right)=\sigma\left(\mathbf{z}_{i}^{\top} \mathbf{z}_{j}\right)$
其中:
- $\mathbf{A}$ 是邻接矩阵
- $\sigma(\cdot)$ 是 logistic sigmoid function.
class InnerProductDecoder(nn.Module):
"""Decoder for using inner product for prediction.""" def __init__(self, dropout, act=torch.sigmoid):
super(InnerProductDecoder, self).__init__()
self.dropout = dropout
self.act = act def forward(self, z):
z = F.dropout(z, self.dropout, training=self.training)
adj = self.act(torch.mm(z, z.t()))
return adj self.dc = InnerProductDecoder(dropout, act=lambda x: x) adj = self.dc(z)
Learning:优化变分下界 $\mathcal{L}$ 的参数 $W_i$ :
$\mathcal{L}=\mathbb{E}_{q(\mathbf{Z} \mid \mathbf{X}, \mathbf{A})}[\log p(\mathbf{A} \mid \mathbf{Z})]-\mathrm{KL}[q(\mathbf{Z} \mid \mathbf{X}, \mathbf{A}) \| p(\mathbf{Z})]$
其中:
- $\operatorname{KL}[q(\cdot) \| p(\cdot)]$ 代表着 $q(\cdot)$ 和 $p(\cdot)$ 之间的 KL散度。
- 高斯先验 $p(\mathbf{Z})=\prod_{i} p\left(\mathbf{z}_{\mathbf{i}}\right)=\prod_{i} \mathcal{N}\left(\mathbf{z}_{i} \mid 0, \mathbf{I}\right)$
Non-probabilistic graph auto-encoder (GAE) model
计算表示向量 $Z$ 和重建的邻接矩阵 $\hat{\mathbf{A}}$
$\hat{\mathbf{A}}=\sigma\left(\mathbf{Z Z}^{\top}\right), \text { with } \quad \mathbf{Z}=\operatorname{GCN}(\mathbf{X}, \mathbf{A})$
2 Experiments on link prediction
引文网络中链接预测任务的结果如 Table 1 所示。

GAE* and VGAE* denote experiments without using input features, GAE and VGAE use input features.
论文解读(VGAE)《Variational Graph Auto-Encoders》的更多相关文章
- 论文解读《Bilinear Graph Neural Network with Neighbor Interactions》
论文信息 论文标题:Bilinear Graph Neural Network with Neighbor Interactions论文作者:Hongmin Zhu, Fuli Feng, Xiang ...
- 论文解读《Cauchy Graph Embedding》
Paper Information Title:Cauchy Graph EmbeddingAuthors:Dijun Luo, C. Ding, F. Nie, Heng HuangSources: ...
- 论文解读(GraphMAE)《GraphMAE: Self-Supervised Masked Graph Autoencoders》
论文信息 论文标题:GraphMAE: Self-Supervised Masked Graph Autoencoders论文作者:Zhenyu Hou, Xiao Liu, Yukuo Cen, Y ...
- 论文解读(KP-GNN)《How Powerful are K-hop Message Passing Graph Neural Networks》
论文信息 论文标题:How Powerful are K-hop Message Passing Graph Neural Networks论文作者:Jiarui Feng, Yixin Chen, ...
- 论文解读(SR-GNN)《Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data》
论文信息 论文标题:Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data论文作者:Qi Zhu, ...
- 论文解读(LG2AR)《Learning Graph Augmentations to Learn Graph Representations》
论文信息 论文标题:Learning Graph Augmentations to Learn Graph Representations论文作者:Kaveh Hassani, Amir Hosein ...
- 论文解读(GCC)《Efficient Graph Convolution for Joint Node RepresentationLearning and Clustering》
论文信息 论文标题:Efficient Graph Convolution for Joint Node RepresentationLearning and Clustering论文作者:Chaki ...
- 论文解读(AGC)《Attributed Graph Clustering via Adaptive Graph Convolution》
论文信息 论文标题:Attributed Graph Clustering via Adaptive Graph Convolution论文作者:Xiaotong Zhang, Han Liu, Qi ...
- 论文解读(DGI)《DEEP GRAPH INFOMAX》
论文标题:DEEP GRAPH INFOMAX 论文方向:图像领域 论文来源:2019 ICLR 论文链接:https://arxiv.org/abs/1809.10341 论文代码:https:// ...
随机推荐
- An incompatible version 1.1.1 of the APR based Apache Tomcat Native library is installed, while Tomcat requires version 1.1.17
[问题现象]: 启动Tomcat时报如下类似错误信息: An incompatible version 1.1.12 of the APR based Apache Tomcat Native lib ...
- 10、架构--keepalive、四层负载均衡
笔记 1.晨考 1.HTTPS的作用,怎么实现的呢? 2.全栈部署HTTPS 只需在代理中部署HTTPS 3.反向代理 BBS 步骤 1.部署WEB机器 2.部署代理 4.如果 LB01 宕机了,怎么 ...
- Kubeadm部署-Kubernetes-1.18.6集群
环境配置 IP hostname 操作系统 10.11.66.44 k8s-master centos7.6 10.11.66.27 k8s-node1 centos7.7 10.11.66.28 k ...
- Large Sacle Distributed Deep Networks
本文是谷歌发表在NeurIPS 2012上的一篇论文,主要讨论了在几万个CPU节点上训练大规模深度网络的问题,并提出了一个名为DistBelief的软件框架.在该框架下实现了两种大规模分布式训练算法: ...
- 带分数--第四届蓝桥杯省赛C++B/C组
第四届蓝桥杯省赛C++B/C组----带分数 思路: 1.先枚举全排列 2.枚举位数 3.判断是否满足要求 这道题也就是n=a+b/c,求出符合要求的abc的方案数.进行优化时,可以对等式进行改写,改 ...
- XStream: Stream Processing Platform at Facebook
这是Facebook在FlinkForward2021上的一个talk, 主题如下 在前面的论文中分析了Facebook的实时计算引擎的设计和选型的考量,里面提到了Facebook的实时计算引擎为了满 ...
- 图解|12张图告诉你MySQL的主键查询为什么这么快
这是图解MySQL的第3篇文章,这篇文章会让大家清楚地明白: 什么是InnoDB行格式?InnoDB页是什么? InnoDB页和InnoDB行格式都有哪些字段信息? 为什么推荐使用自增ID作为主键,而 ...
- k8s容器拷贝文件到本地、本地文件拷贝到k8s容器
k8s容器拷贝文件到本地 kubectl cp qzcsbj/order-b477c8947-tr8rz:/tmp/jstack.txt /root/test/jstack.txt 本地文件拷贝到k8 ...
- RFC2889——拥塞控制测试
一.简介 RFC 2889为LAN交换设备的基准测试提供了方法学,它将RFC 2544中为网络互联设备基准测试所定义的方法学扩展到了交换设备,提供了交换机转发性能(Forwarding Perform ...
- Linux查看进程的4种方法
转至:https://www.cnblogs.com/hml-blog-com/p/11558369.html 进程是在 CPU 及内存中运行的程序代码,而每个进程可以创建一个或多个进程(父子进程). ...