图嵌入模型综述

doi:10.3778/j.issn.1673-9418.2104020

计算机科学与探索 ›› 2022, Vol. 16 ›› Issue (1): 59-87.DOI: 10.3778/j.issn.1673-9418.2104020

图嵌入模型综述

袁立宁¹, 李欣², 王晓冬³, 刘钊⁴^,⁺()

1.中国人民公安大学信息网络安全学院,北京 100038
2.天津市公安局河西分局科技信息化支队,天津 300202
3.天津市公安局河东分局科技信息化支队,天津 300171
4.中国人民公安大学新型犯罪研究中心,北京 100038

收稿日期:2021-04-08 修回日期:2021-09-07 出版日期:2022-01-01 发布日期:2021-09-13
通讯作者: + E-mail: liuzhao@ppsuc.edu.cn
作者简介:袁立宁(1995—),男,硕士研究生,CCF学生会员,主要研究方向为机器学习、图神经网络等。
李欣(1987—),男,硕士,主要研究方向为机器学习、公安信息化等。
王晓冬(1980—),男,中级工程师,主要研究方向为警务大数据、技术侦查等。
刘钊(1981—),男,博士,讲师, 主要研究方向为机器学习、计算机视觉。
基金资助:
中央高校基本科研业务费专项资金(2019JKF425);国家重点研发计划(2018YFC0809800)

Graph Embedding Models: A Survey

YUAN Lining¹, LI Xin², WANG Xiaodong³, LIU Zhao⁴^,⁺()

1. School of Information Network Security, People's Public Security University of China, Beijing 100038, China
2. Science and Informatization Division, Hexi Branch of Tianjin Public Security Bureau, Tianjin 300202, China
3. Science and Informatization Division, Hedong Branch of Tianjin Public Security Bureau, Tianjin 300171, China
4. Research Center for New Crimes, People's Public Security University of China, Beijing 100038, China

Received:2021-04-08 Revised:2021-09-07 Online:2022-01-01 Published:2021-09-13
About author:YUAN Lining, born in 1995, M.S. candidate, student member of CCF. His research interests include machine learning, graph neural network, etc.
LI Xin, born in 1987, M.S. His research interests include machine learning, policing information system, etc.
WANG Xiaodong, born in 1980, intermediate engineer. His research interests include police big data, technical investigation, etc.
xml:lang="en"LIU Zhao, born in 1981, Ph.D., lecturer. His research interests include machine learning and computer vision.
Supported by:
Fundamental Research Funds for the Central Universities of China(2019JKF425);National Key Research and Development Program of China(2018YFC0809800)

摘要/Abstract

摘要：

图分析用于深入挖掘图数据的内在特征,然而图作为非欧几里德数据,传统的数据分析方法普遍存在较高的计算量和空间开销。图嵌入是一种解决图分析问题的有效方法,其将原始图数据转换到低维空间并保留关键信息,从而提升节点分类、链接预测、节点聚类等下游任务的性能。与以往的研究不同,同时对静态图和动态图嵌入文献进行全面回顾,提出一种静态图嵌入和动态图嵌入通用分类方法,即基于矩阵分解的图嵌入、基于随机游走的图嵌入、基于自编码器的图嵌入、基于图神经网络（GNN）的图嵌入和基于其他方法的图嵌入。其次,对静态图和动态图方法的理论相关性进行分析,对模型核心策略、下游任务和数据集进行全面总结。最后,提出了四个图嵌入的潜在研究方向。

关键词: 图嵌入, 静态图嵌入, 动态图嵌入, 随机游走, 图神经网络（GNN）

Abstract:

Effective graph analysis methods can reveal the intrinsic characteristics of graph data. However, graph is non-Euclidean data, which leads to high computation and space cost while applying traditional methods. Graph embedding is an efficient method for graph analysis. It converts original graph data into a low-dimensional space and retains key information to improve the performance of downstream tasks such as node classification, link prediction, and node clustering. Different from previous studies, this paper focuses on both static and dynamic graph embedding. Firstly, this paper proposes a universal taxonomy of static and dynamic methods, including matrix factorization based methods, random walk based methods, autoencoder based methods, graph neural networks (GNN) based methods and other embedding methods. Secondly, this paper analyzes the theoretical relevance of static and dynamic methods, and comprehensively summarizes the core strategy, downstream tasks and datasets. Finally, this paper proposes four potential research directions of graph embedding.

Key words: graph embedding, static graph embedding, dynamic graph embedding, random walk, graph neural networks (GNN)

中图分类号:

TP391

袁立宁, 李欣, 王晓冬, 刘钊. 图嵌入模型综述[J]. 计算机科学与探索, 2022, 16(1): 59-87.

YUAN Lining, LI Xin, WANG Xiaodong, LIU Zhao. Graph Embedding Models: A Survey[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(1): 59-87.

图/表 35

图1 快照型和连续时间型动态图

Fig.1 Snapshot and continuous-time dynamic graphs

图2 图嵌入的一般过程

Fig.2 General framework for graph embedding

表1 符号及定义

Table 1 Symbols and definitions

符号	说明
A	邻接矩阵
D	顶点度矩阵
L	拉普拉斯矩阵
X	特征矩阵
S	相似度矩阵
W	系数矩阵
G	静态图
$\mathcal{G}$	动态图
V	节点集
E	边集
d	嵌入维度
Y	嵌入表示

图3 图嵌入内容体系

Fig.3 Content system of graph embedding

图4 图嵌入模型分类汇总

Fig.4 Categorization and summary of graph embedding models

图5 基于矩阵分解的静态图嵌入模型框架

Fig.5 Framework of eigenvalue factorization in static graph embedding

图6 LLE步骤

Fig.6 Steps of LLE

图7 HOPE模型框架

Fig.7 Framework of HOPE

图8 基于矩阵分解的动态图嵌入模型框架

Fig.8 Framework of matrix factorization in dynamic graph embedding

图9 DANE模型结构

Fig.9 Framework of DANE

图10 Deepwalk模型结构

Fig.10 Framework of Deepwalk

图11 node2vec中的随机游走过程

Fig.11 Random walk procedure in node2vec

图12 TriDNR模型结构

Fig.12 Architecture of TriDNR model

图13 SDNE模型结构

Fig.13 Framework of SDNE

图14 DynGEM模型结构

Fig.14 Framework of DynGEM

图15 dyngraph2vec变体结构

Fig.15 Variations of dyngraph2vec

图16 NetWalk异常检测的流程

Fig.16 Workflow of NetWalk for anomaly detection

图17 多层GCN结构

Fig.17 Framework of multi-layer GCN

图18 图解GraphSAGE采样和聚合方式

Fig.18 Visual illustration of GraphSAGE sampling and aggregation approach

图19 MF-GCN模型结构

Fig.19 Framework of MF-GCN

图20 DySAT模型结构

Fig.20 Framework of DySAT

图21 TemporalGAT模型结构

Fig.21 Framework of TemporalGAT

图22 DRNE模型结构

Fig.22 Framework of DRNE

图23 Graphormer模型结构

Fig.23 Framework of Graphormer

表2 静态图嵌入模型策略归纳

Table 2 Strategies of static graph embedding

模型分类	模型	时间	模型策略
矩阵分解	LLE^[24]	2000	构造邻域保持映射,最小化重建损失函数
	GF^[13]	2013	分解邻接矩阵,利用向量内积捕捉边的存在
	GraRep^[25]	2015	使用SVD分解k步对数转移概率矩阵
	HOPE^[27]	2016	GSVD分解相似度矩阵,L2范数保持高阶相似度
	NGE^[30]	2013	使用NMF将输入分解为系数矩阵和嵌入矩阵
	LE^[32]	2001	保持相连节点在嵌入空间尽可能靠近
	CGE^[33]	2011	修改LE损失函数,保持低权值节点对相似性
	SPE^[34]	2009	利用核矩阵生成关系矩阵 $A ˜$ ,最小化 $A$ 和 $A ˜$ 的差异
随机游走	Deepwalk^[49]	2014	使用随机游走采样节点,Skip-Gram最大化节点共现概率
	node2vec^[50]	2016	在Deepwalk的基础上引入有偏的随机游走
	HARP^[51]	2017	利用原始图生成保留全局结构的压缩图
	Walklets^[52]	2016	改进Deepwalk,捕获节点与社区的从属关系并建模
	TriDNR^[54]	2016	最大化节点标签、节点邻域、节点内容的共现概率
自编码器	GraphEncoder^[63]	2014	利用L2损失函数重构图相似度矩阵
	SDNE^[64]	2016	使用有监督和无监督组件分别保持一阶和二阶相似度
	DNGR^[65]	2016	随机冲浪捕获图结构,生成PPMI矩阵输入SDAE
	DNE-APP^[67]	2017	使用PPMI度量和k步转移矩阵构建相似度聚合矩阵
	VGAE^[69]	2016	引入VAE,使用GCN编码器,使用内积解码器
	GALA^[73]	2020	编码器执行拉普拉斯平滑,解码器执行拉普拉斯锐化
	ANE^[76]	2018	施加对抗性正则化避免流形断裂
图神经网络	GCN^[70]	2016	利用谱卷积一阶近似提高层间传播效率
	GraphSAGE^[85]	2017	采样和聚合节点的局部邻域特征训练聚合器函数
	GAT^[95]	2017	在GCN的基础上引入self-attention和multi-head attention
	GIN^[98]	2018	利用GNN和WL图同构测试保留图结构信息
	MF-GCN^[100]	2020	使用多个局部GCN滤波器提取节点特征
	GraphAIR^[102]	2020	邻域聚合模块融合节点特征表示,邻域交互模块通过乘法运算显示建模
	SDGNN^[103]	2021	在GNN的基础引入地位理论和平衡理论
其他	LINE^[116]	2015	分别优化一阶和二阶相似度,将嵌入向量进行拼接
	DNRE^[117]	2018	直接使用LSTM聚合邻域信息重建节点嵌入
	Graphormer^[119]	2021	在标准Transformer基础上,引入有中心性编码、空间编码和边编码

表2 静态图嵌入模型策略归纳

Table 2 Strategies of static graph embedding

模型分类	模型	时间	模型策略
矩阵分解	LLE^[24]	2000	构造邻域保持映射,最小化重建损失函数
	GF^[13]	2013	分解邻接矩阵,利用向量内积捕捉边的存在
	GraRep^[25]	2015	使用SVD分解k步对数转移概率矩阵
	HOPE^[27]	2016	GSVD分解相似度矩阵,L2范数保持高阶相似度
	NGE^[30]	2013	使用NMF将输入分解为系数矩阵和嵌入矩阵
	LE^[32]	2001	保持相连节点在嵌入空间尽可能靠近
	CGE^[33]	2011	修改LE损失函数,保持低权值节点对相似性
	SPE^[34]	2009	利用核矩阵生成关系矩阵 $A ˜$ ,最小化 $A$ 和 $A ˜$ 的差异
随机游走	Deepwalk^[49]	2014	使用随机游走采样节点,Skip-Gram最大化节点共现概率
	node2vec^[50]	2016	在Deepwalk的基础上引入有偏的随机游走
	HARP^[51]	2017	利用原始图生成保留全局结构的压缩图
	Walklets^[52]	2016	改进Deepwalk,捕获节点与社区的从属关系并建模
	TriDNR^[54]	2016	最大化节点标签、节点邻域、节点内容的共现概率
自编码器	GraphEncoder^[63]	2014	利用L2损失函数重构图相似度矩阵
	SDNE^[64]	2016	使用有监督和无监督组件分别保持一阶和二阶相似度
	DNGR^[65]	2016	随机冲浪捕获图结构,生成PPMI矩阵输入SDAE
	DNE-APP^[67]	2017	使用PPMI度量和k步转移矩阵构建相似度聚合矩阵
	VGAE^[69]	2016	引入VAE,使用GCN编码器,使用内积解码器
	GALA^[73]	2020	编码器执行拉普拉斯平滑,解码器执行拉普拉斯锐化
	ANE^[76]	2018	施加对抗性正则化避免流形断裂
图神经网络	GCN^[70]	2016	利用谱卷积一阶近似提高层间传播效率
	GraphSAGE^[85]	2017	采样和聚合节点的局部邻域特征训练聚合器函数
	GAT^[95]	2017	在GCN的基础上引入self-attention和multi-head attention
	GIN^[98]	2018	利用GNN和WL图同构测试保留图结构信息
	MF-GCN^[100]	2020	使用多个局部GCN滤波器提取节点特征
	GraphAIR^[102]	2020	邻域聚合模块融合节点特征表示,邻域交互模块通过乘法运算显示建模
	SDGNN^[103]	2021	在GNN的基础引入地位理论和平衡理论
其他	LINE^[116]	2015	分别优化一阶和二阶相似度,将嵌入向量进行拼接
	DNRE^[117]	2018	直接使用LSTM聚合邻域信息重建节点嵌入
	Graphormer^[119]	2021	在标准Transformer基础上,引入有中心性编码、空间编码和边编码

表3 动态图嵌入模型策略归纳

Table 3 Strategies of dynamic graph embedding

模型分类	模型	时间	模型策略
矩阵分解	DANE^[36]	2017	拉普拉斯特征映射捕获t时刻的结构和属性信息,矩阵摄动理论更新动态信息
	DHPE^[38]	2018	GSVD分解各时刻Katz矩阵,矩阵摄动理论更新动态信息
	TRIP^[40]	2015	利用图中三角形个数构建特征函数,将特征对矩阵映射成嵌入向量
	TIMERS^[41]	2017	SVD最大误差界重启,消除增量更新积累的误差
	DWSF^[45]	2017	将图中有限监督信息合并为标签,并在每次迭代中更新
随机游走	CTDNE^[56]	2018	按照时间顺序对边进行遍历
	dynnode2vec^[57]	2018	node2vec初始化快照,对变化点执行随机游走,利用Skip-Gram更新动态信息
	STWalk^[59]	2017	捕捉规定时间窗内节点的变化
	tNodeEmbed^[60]	2019	模仿句子嵌入作为节点嵌入,捕捉节点角色和边的动态变化
自编码器	DynGEM^[78]	2018	提出PropSize动态调节神经元个数,同时引入L1和L2正则化
	dyngraph2vec^[79]	2019	组合AE和LSTM,构建不同的编码器和解码器组合
	NetWalk^[81]	2018	同时最小化节点距离和自编码器重构误差
	BurstGraph^[84]	2019	将动态演化分为一般演化和突发演化,RNN捕捉各时刻的图结构
	HVGNN^[92]	2021	采用基于TGNN的双曲VGAE
图神经网络	DyRep^[106]	2018	基于自我传播、外源驱动、局部嵌入传播更新节点表示
	DySAT^[108]	2020	结构注意力提取邻域特征,时间注意力捕捉多个时刻的表示
	EvolveGCN^[110]	2019	在每个时刻使用RNN调整GCN参数
	DGNN^[111]	2020	使用时态信息增强LSTM作为更新框架
	TemporalGAT^[112]	2020	集成GAT和TCN,self-attention应用于邻域,TCN用于动态信息更新
其他	HTNE^[120]	2018	Hawkes捕捉过去时刻对当前时刻邻域的影响,Skip-Gram更新动态信息
	DynamicTriad^[122]	2018	通过闭合三元组和开放三元组模拟图的动态演化
	M²DNE^[125]	2019	微观动态描述结构的形成,宏观动态描述规模的演化,利用二者交互生成嵌入
	CAW^[126]	2021	回溯多个时刻的相邻链接编码因果关系,根据特征位置计数编码相应节点标识

表3 动态图嵌入模型策略归纳

Table 3 Strategies of dynamic graph embedding

模型分类	模型	时间	模型策略
矩阵分解	DANE^[36]	2017	拉普拉斯特征映射捕获t时刻的结构和属性信息,矩阵摄动理论更新动态信息
	DHPE^[38]	2018	GSVD分解各时刻Katz矩阵,矩阵摄动理论更新动态信息
	TRIP^[40]	2015	利用图中三角形个数构建特征函数,将特征对矩阵映射成嵌入向量
	TIMERS^[41]	2017	SVD最大误差界重启,消除增量更新积累的误差
	DWSF^[45]	2017	将图中有限监督信息合并为标签,并在每次迭代中更新
随机游走	CTDNE^[56]	2018	按照时间顺序对边进行遍历
	dynnode2vec^[57]	2018	node2vec初始化快照,对变化点执行随机游走,利用Skip-Gram更新动态信息
	STWalk^[59]	2017	捕捉规定时间窗内节点的变化
	tNodeEmbed^[60]	2019	模仿句子嵌入作为节点嵌入,捕捉节点角色和边的动态变化
自编码器	DynGEM^[78]	2018	提出PropSize动态调节神经元个数,同时引入L1和L2正则化
	dyngraph2vec^[79]	2019	组合AE和LSTM,构建不同的编码器和解码器组合
	NetWalk^[81]	2018	同时最小化节点距离和自编码器重构误差
	BurstGraph^[84]	2019	将动态演化分为一般演化和突发演化,RNN捕捉各时刻的图结构
	HVGNN^[92]	2021	采用基于TGNN的双曲VGAE
图神经网络	DyRep^[106]	2018	基于自我传播、外源驱动、局部嵌入传播更新节点表示
	DySAT^[108]	2020	结构注意力提取邻域特征,时间注意力捕捉多个时刻的表示
	EvolveGCN^[110]	2019	在每个时刻使用RNN调整GCN参数
	DGNN^[111]	2020	使用时态信息增强LSTM作为更新框架
	TemporalGAT^[112]	2020	集成GAT和TCN,self-attention应用于邻域,TCN用于动态信息更新
其他	HTNE^[120]	2018	Hawkes捕捉过去时刻对当前时刻邻域的影响,Skip-Gram更新动态信息
	DynamicTriad^[122]	2018	通过闭合三元组和开放三元组模拟图的动态演化
	M²DNE^[125]	2019	微观动态描述结构的形成,宏观动态描述规模的演化,利用二者交互生成嵌入
	CAW^[126]	2021	回溯多个时刻的相邻链接编码因果关系,根据特征位置计数编码相应节点标识

表4 静态图数据集统计信息

Table 4 Statistics of static graph datasets

统计项	20-NewsGroup	Flickr	DBLP	YouTube	Wikipedia	Cora	CiteSeer	Pubmed	Yelp
#Nodes	1 720,3 224,5 141	80 513	29 199	1 138 499	2 405	2 708	3 327	19 717	6 569
#Edges	Fully connected	5 899 882	133 664	2 990 443	17 981	5 429	4 732	44 338	95 361
#Features	—	—	—	—	4 973	1 433	3 703	500	—
#Labels	3,6,9	195	4	47	17	7	6	3	—

表5 动态图数据集统计信息

Table 5 Statistics of dynamic graph datasets

统计项	Epinions	Hep-th	AS	Enron	UCI
#Nodes	14 180	1 424~7 980	7 716	184	1 809
#Edges	227 642	2 556~21 036	10 695~26 467	63~591	16 822
#Features	9 936	—	—	—	—
#Labels	20	—	—	—	—
#Time Steps	16	60	100	128	13

图24 网络重构性能对比

Fig.24 Performance comparison of graph reconstruction

图25 静态图节点分类性能对比

Fig.25 Performance comparison of static graph node classification

表6 动态图节点分类性能对比

Table 6 Performance comparison of dynamic graph node classification %

Index	Deepwalk	node2vec	LINE	DANE	tNodeEmbed	CTDNE	HTNE	DynamicTriad	M²DNE
micro-F1	69.65	75.20	67.56	74.53	82.20	71.70	71.40	71.10	69.75
macro-F1	72.37	23.50	70.97	75.69	50.40	8.30	6.90	5.50	69.71

表7 链接预测性能对比

Table 7 Performance comparison of link prediction %

Index	Deepwalk	GAE	VGAE	Linear-GAE	Linear-VGAE	GALA	GraphSAGE	MF-GCN	GraphAIR
AUC	80.5	89.5	90.8	91.5	91.6	94.4	93.7	92.4	95.0
AP	83.6	89.9	92.0	92.9	93.1	94.8	—	—	—

图26 节点聚类性能对比

Fig.26 Performance comparison of node clustering

图27 异常检测性能对比

Fig.27 Performance comparison of anomaly detection

图28 不同模型的可视化结果

Fig.28 Visualization of different models

参考文献 157

[1]	宋雨萌, 谷峪, 李芳芳, 等. 人工智能赋能的查询处理与优化新技术研究综述[J]. 计算机科学与探索, 2020, 14(7):1081-1103.
	SONG Y M, GU Y, LI F F, et al. Survey on AI powered new techniques for query processing and optimization[J]. Journal of Frontiers of Computer Science and Technology, 2020, 14(7):1081-1103.
[2]	TRONCOSO F, WEBER R. A novel approach to detect associations in criminal networks[J]. Decision Support Systems, 2020, 128:113159. DOI URL
[3]	GUO S N, LIN Y F, FENG N, et al. Attention based spatial-temporal graph convolutional networks for traffic flow forecasting[C]// Proceedings of the 33rd AAAI Conference on Artificial Intelligence, the 31st Innovative Applications of Artificial Intelligence Conference, the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, Honolulu, Jan 27-Feb 1, 2019. Menlo Park: AAAI, 2019: 922-929.
[4]	GU J X, WANG Z H, KUEN J, et al. Recent advances in convolutional neural networks[J]. Pattern Recognition, 2018, 77:354-377. DOI URL
[5]	SALEHINEJAD H, SANKAR S, BARFETT J, et al. Recent advances in recurrent neural networks[J]. arXiv:1801.01078, 2017.
[6]	LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553):436-444. DOI URL
[7]	BHAGAT S, CORMODE G, MUTHUKRISHNAN S. Node classification in social networks[M]//AGGARWALC C.Social Network Data Analytics. Berlin, Heidelberg: Springer, 2011: 115-148.
[8]	LIBEN-NOWELL D, KLEINBERG J. The link-prediction problem for social networks[J]. Journal of the American Society for Information Science and Technology, 2007, 58(7):1019-1031. DOI URL
[9]	DING C H Q, HE X F, ZHA H Y, et al. A min-max cut algorithm for graph partitioning and data clustering[C]// Proceedings of the 2001 IEEE International Conference on Data Mining, San Jose, Nov 29-Dec 2, 2001. Washington:IEEE Computer Society, 2001: 107-114.
[10]	VAN DER MAATEN L, HINTON G. Visualizing data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9(11):2579-2605.
[11]	QIU J Z, TANG J, MA H, et al. DeepInf: social influence prediction with deep learning[C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, London, Aug 19-23, 2018. New York: ACM, 2018: 2110-2119.
[12]	SILVEIRA T, ZHANG M, LIN X, et al. How good your recommender system is? A survey on evaluations in recom-mendation[J]. International Journal of Machine Learning and Cybernetics, 2019, 10(5):813-831. DOI URL
[13]	AHMED A, SHERVASHIDZE N, NARAYANAMURTHY S M, et al. Distributed large-scale natural graph factorization[C]// Proceedings of the 22nd International World Wide Web Conference, Rio de Janeiro, May 13-17, 2013. New York: ACM, 2013: 37-48.
[14]	LOVÁSZ L. Random walks on graphs: a survey[J]. Com-binatorics, Paul Erdös is Eighty, 1993, 2(1):1-46.
[15]	GOLDBERG Y, LEVY O. word2vec explained: deriving Mikolov et al.’s negative-sampling word-embedding method[J]. arXiv:1402.3722, 2014.
[16]	CAI H, ZHENG V W, CHANG K C. A comprehensive survey of graph embedding: problems, techniques, and applications[J]. IEEE Transactions on Knowledge and Data Engineering, 2018, 30(9):1616-1637. DOI URL
[17]	GOYAL P, FERRARA E. Graph embedding techniques, applications, and performance: a survey[J]. Knowledge-Based Systems, 2018, 151:78-94. DOI URL
[18]	CHEN F X, WANG Y C, WANG B, et al. Graph repres-entation learning: a survey[J]. APSIPA Transactions on Signal and Information Processing, 2020, 9:e15. DOI URL
[19]	CUI P, WANG X, PEI J, et al. A survey on network embedding[J]. IEEE Transactions on Knowledge and Data Engineering, 2018, 31(5):833-852. DOI URL
[20]	XIE Y, LI C, YU B, et al. A survey on dynamic network embedding[J]. arXiv:2006.08093, 2020.
[21]	SKARDINGA J, GABRYS B, MUSIAL K. Foundations and modelling of dynamic networks using dynamic graph neural networks: a survey[J]. IEEE Access, 2021, 9:79143-79168. DOI URL
[22]	NG A. Sparse autoencoder[J]. CS294A Lecture Notes, 2011, 72:1-19.
[23]	SCARSELLI F, GORI M, TSOI A C, et al. The graph neural network model[J]. IEEE Transactions on Neural Networks, 2008, 20(1):61-80. DOI URL
[24]	ROWEIS S T, SAUL L K. Nonlinear dimensionality red-uction by locally linear embedding[J]. Science, 2000, 290(5500):2323-2326. DOI URL
[25]	CAO S S, LU W, XU Q K. GraRep: learning graph repres-entations with global structural information[C]// Proceedings of the 24th ACM International Conference on Information and Knowledge Management, Melbourne, Oct 19-23, 2015. New York: ACM, 2015: 891-900.
[26]	LEVY O, GOLDBERG Y. Neural word embedding as implicit matrix factorization[C]// Proceedings of the Annual Conference on Neural Information Processing Systems 2014, Montreal, Dec 8-13, 2014. Red Hook: Curran Associates, 2014: 2177-2185.
[27]	OU M D, CUI P, PEI J, et al. Asymmetric transitivity preserving graph embedding[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, Aug 13-17, 2016. New York: ACM, 2016: 1105-1114.
[28]	KATZ L. A new status index derived from sociometric analysis[J]. Psychometrika, 1953, 18(1):39-43. DOI URL
[29]	PAIGE C C, SAUNDERS M A. Towards a generalized singular value decomposition[J]. SIAM Journal on Numerical Analysis, 1981, 18(3):398-405. DOI URL
[30]	YANG J C, YANG S C, FU Y, et al. Non-negative graph embedding[C]// Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, Jun 24-26, 2008. Washington: IEEE Computer Society, 2008: 1-8.
[31]	LEE D D, SEUNG H S. Learning the parts of objects by non-negative matrix factorization[J]. Nature, 1999, 401(6755):788-791. DOI URL
[32]	BELKIN M, NIYOGI P. Laplacian Eigenmaps and spectral techniques for embedding and clustering[C]// Proceedings of the Neural Information Processing Systems: Natural and Synthetic, Vancouver, Dec 3-8, 2001. Cambridge: MIT Press, 2001: 585-591.
[33]	LUO D J, DING C H Q, NIE F P, et al. Cauchy graph embe-dding[C]// Proceedings of the 28th International Conference on Machine Learning, Bellevue, Jun 28-Jul 2, 2011. Madison: Omnipress, 2011: 553-560.
[34]	SHAW B, JEBARA T. Structure preserving embedding[C]// Proceedings of the 26th Annual International Conference on Machine Learning, Montreal, Jun 14-18, 2009. New York: ACM, 2009: 937-944.
[35]	LI R C. Matrix perturbation theory[M]//HOGBEN L. 2nd ed. Handbook of Linear Algebra. Boca Raton: CRC Press, 2013.
[36]	LI J D, DANI H, HU X, et al. Attributed network embe-dding for learning in a dynamic environment[C]// Proceedings of the 2017 ACM on Conference on Information and Know-ledge Management, Singapore, Nov 6-10, 2017. New York: ACM, 2017: 387-396.
[37]	HARDOON D R, SZEDMAK S, SHAWE-TAYLOR J. Canonical correlation analysis: an overview with application to learning methods[J]. Neural Computation, 2004, 16(12):2639-2664. DOI URL
[38]	ZHU D Y, CUI P, ZHANG Z W, et al. High-order proximity preserved embedding for dynamic networks[J]. IEEE Tran-sactions on Knowledge and Data Engineering, 2018, 30(11):2134-2144.
[39]	STRANG G, STRANG G, STRANG G, et al. Introduction to linear algebra[M]. Wellesley: Wellesley-Cambridge Press, 1993.
[40]	CHEN C, TONG H H. Fast Eigen-functions tracking on dynamic graphs[C]// Proceedings of the 2015 SIAM Inter-national Conference on Data Mining, Vancouver, Apr 30 - May 2, 2015. Philadelphia: SIAM, 2015: 559-567.
[41]	TSOURAKAKIS C E. Fast counting of triangles in large real networks without counting: algorithms and laws[C]// Proceedings of the 8th IEEE International Conference on Data Mining, Pisa, Dec 15-19, 2008. Washington: IEEE Com-puter Society, 2008: 608-617.
[42]	TSOURAKAKIS C E. Counting triangles in real-world networks using projections[J]. Knowledge and Information Systems, 2011, 26(3):501-520. DOI URL
[43]	ZHANG Z W, CUI P, PEI J, et al. Timers: error-bounded SVD restart on dynamic networks[C]// Proceedings of the 32nd AAAI Conference on Artificial Intelligence, the 30th Innovative Applications of Artificial Intelligence, and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence, New Orleans, Feb 2-7, 2018. Menlo Park: AAAI, 2018: 224-231.
[44]	AHMED N M, CHEN L, WANG Y L, et al. DeepEye: link prediction in dynamic networks based on non-negative matrix factorization[J]. Big Data Mining and Analytics, 2018, 1(1):19-33. DOI URL
[45]	SEYEDI S A, MORADI P, TAB F A. A weakly-supervised factorization method with dynamic graph embedding[C]// Proceedings of the 2017 Artificial Intelligence and Signal Processing Conference, Shiraz, Oct 25-27, 2017. Piscataway: IEEE, 2017: 213-218.
[46]	WANG Y X, ZHANG Y J. Nonnegative matrix factorization: a comprehensive review[J]. IEEE Transactions on Knowledge and Data Engineering, 2012, 25(6):1336-1353. DOI URL
[47]	TRIGEORGIS G, BOUSMALIS K, ZAFEIRIOU S, et al. A deep matrix factorization method for learning attribute representations[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 39(3):417-429. DOI URL
[48]	LIU Y, LEE J, PARK M, et al. Learning to propagate labels: transductive propagation network for few-shot learning[J]. arXiv:1805.10002, 2018.
[49]	PEROZZI B, AL-RFOU R, SKIENA S. DeepWalk: online learning of social representations[C]// Proceedings of the 20th ACM SIGKDD International Conference on Know-ledge Discovery and Data Mining, New York, Aug 24-27, 2014. New York: ACM, 2014: 701-710.
[50]	GROVER A, LESKOVEC J. node2vec: scalable feature learning for networks[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, Aug 13-17, 2016. New York: ACM, 2016: 855-864.
[51]	CHEN H C, PEROZZI B, HU Y F, et al. Harp: hierarchical representation learning for networks[C]// Proceedings of the 32nd AAAI Conference on Artificial Intelligence, the 30th Innovative Applications of Artificial Intelligence, and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence, New Orleans, Feb 2-7, 2018. Menlo Park: AAAI, 2018: 2127-2134.
[52]	YANG C, LIU Z Y. Comprehend deepwalk as matrix factor-ization[J]. arXiv:1501.00358, 2015.
[53]	PEROZZI B, KULKARNI V, SKIENA S. Walklets: multiscale graph embeddings for interpretable network classification[J]. arXiv:1605.02115, 2016.
[54]	PAN S R, WU J, ZHU X Q, et al. Tri-party deep network representation[C]// Proceedings of the 25th International Joint Conference on Artificial Intelligence, New York, Jul 9-15, 2016. Menlo Park: AAAI, 2016: 1895-1901.
[55]	SAJJAD H P, DOCHERTY A, TYSHETSKIY Y. Efficient representation learning using random walks for dynamic graphs[J]. arXiv:1901.01346, 2019.
[56]	NGUYEN G H, LEE J B, ROSSI R A, et al. Continuous-time dynamic network embeddings[C]// Companion Procee-dings of the Web Conference, Lyon, Apr 23-27, 2018. New York: ACM, 2018: 969-976.
[57]	MAHDAVI S, KHOSHRAFTAR S, AN A J. Dynnode2vec: scalable dynamic network embedding[C]// Proceedings of the 2018 IEEE International Conference on Big Data, Seattle, Dec 10-13, 2018. Piscataway: IEEE, 2018: 3762-3765.
[58]	KIM Y, CHIU Y I, HANAKI K, et al. Temporal analysis of language through neural language models[J]. arXiv:1405.3515, 2014.
[59]	PANDHRE S, MITTAL H, GUPTA M, et al. STWalk: learning trajectory representations in temporal graphs[C]// Proceedings of the ACM India Joint International Conference on Data Science and Management of Data, Goa, Jan 11-13, 2018. New York: ACM, 2018: 210-219.
[60]	SINGER U, GUY I, RADINSKY K. Node embedding over temporal graphs[J]. arXiv:1903.08889, 2019.
[61]	PALANGI H, DENG L, SHEN Y L, et al. Deep sentence embedding using the long short term memory network: analysis and application to information retrieval[J]. arXiv:1502.06922, 2015.
[62]	BOURLARD H, KAMP Y. Auto-association by multilayer perceptrons and singular value decomposition[J]. Biological Cybernetics, 1988, 59(4):291-294. DOI URL
[63]	TIAN F, GAO B, CUI Q, et al. Learning deep representations for graph clustering[C]// Proceedings of the 28th AAAI Conference on Artificial Intelligence, Québec City, Jul 27 -31, 2014. Menlo Park: AAAI, 2014: 1293-1299.
[64]	WANG D X, CUI P, ZHU W W. Structural deep network embedding[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, Aug 13-17, 2016. New York: ACM, 2016: 1225-1234.
[65]	CAO S S, LU W, XU Q K. Deep neural networks for learning graph representations[C]// Proceedings of the 30th AAAI Conference on Artificial Intelligence, Phoenix, Feb 12-17, 2016. Menlo Park: AAAI, 2016: 1145-1152.
[66]	BULLINARIA J A, LEVY J P. Extracting semantic repres-entations from word co-occurrence statistics: a computational study[J]. Behavior Research Methods, 2007, 39(3):510-526. DOI URL
[67]	SHEN X, CHUNG F L. Deep network embedding with aggregated proximity preserving[C]// Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, Sydney, Jul 31-Aug 3, 2017. New York: ACM, 2017: 40-43.
[68]	KINGMA D P, WELLING M. Auto-encoding variational Bayes[J]. arXiv:1312.6114, 2013.
[69]	KIPF T N, WELLING M. Variational graph auto-encoders[J]. arXiv:1611.07308, 2016.
[70]	KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[J]. arXiv1609.02907, 2016.
[71]	KULLBACK S, LEIBLER R A. On information and suffi-ciency[J]. The Annals of Mathematical Statistics, 1951, 22(1):79-86. DOI URL
[72]	SALHA G, HENNEQUIN R, VAZIRGIANNIS M. Keep it simple: graph autoencoders without graph convolutional networks[J]. arXiv:1910.00942, 2019.
[73]	PARK J, LEE M, CHANG H J, et al. Symmetric graph convolutional autoencoder for unsupervised graph represen-tation learning[C]// Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, Seoul, Oct 27-Nov 2, 2019. Piscataway: IEEE, 2019: 6518-6527.
[74]	CAI D, HE X F, HU Y X, et al. Learning a spatially smooth subspace for face recognition[C]// Proceedings of the 2007 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Minneapolis, Jun 18-23, 2007.Washington: IEEE Computer Society, 2007: 1-7.
[75]	TAUBIN G. A signal processing approach to fair surface design[C]// Proceedings of the 22nd Annual Conference on Computer Graphics and Interactive Techniques, Los Angeles, Aug 6-11, 1995. New York: ACM, 1995: 351-358.
[76]	XIAO Y, XIAO D, HU B B, et al. ANE: network embe-dding via adversarial autoencoders[C]// Proceedings of the 2018 IEEE International Conference on Big Data and Smart Computing, Shanghai, Jan 15-17, 2018. Washington:IEEE Computer Society, 2018: 66-73.
[77]	MAKHZANI A, SHLENS J, JAITLY N, et al. Adversarial autoencoders[J]. arXiv:1511.05644, 2015.
[78]	GOYAL P, KAMRA N, HE X, et al. DynGEM: deep embedding method for dynamic graphs[J]. arXiv:1805.11273, 2018.
[79]	GOYAL P, CHHETRI S R, CANEDO A. Dyngraph2vec: capturing network dynamics using dynamic graph repres-entation learning[J]. Knowledge-Based Systems, 2020, 187:104816. DOI URL
[80]	HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8):1735-1780. DOI URL
[81]	YU W C, CHENG W, AGGARWAL C C, et al. NetWalk: a flexible deep embedding approach for anomaly detection in dynamic networks[C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, London, Aug 19-23, 2018. New York: ACM, 2018: 2672-2681.
[82]	AKOGLU L, FALOUTSOS C. Anomaly, event, and fraud detection in large network datasets[C]// Proceedings of the 6th ACM International Conference on Web Search and Data Mining, Rome, Feb 4-8, 2013. New York: ACM, 2013: 773-774.
[83]	AKOGLU L, TONG H H, KOUTRA D. Graph based anomaly detection and description: a survey[J]. Data Mining and Knowledge Discovery, 2015, 29(3):626-688. DOI URL
[84]	ZHAO Y F, WANG X W, YANG H X, et al. Large scale evolving graphs with burst detection[C]// Proceedings of the 28th International Joint Conference on Artificial Intelligence, Macao, China, Aug 10-16, 2019: 4412-4418.
[85]	HAMILTON W L, YING R, LESKOVEC J. Inductive representation learning on large graphs[J]. arXiv:1706.02216, 2017.
[86]	MITCHELL T J, BEAUCHAMP J J. Bayesian variable selection in linear regression[J]. Journal of the American Statistical Association, 1988, 83(404):1023-1032. DOI URL
[87]	HEARD N A, WESTON D J, PLATANIOTI K, et al. Bayesian anomaly detection methods for social networks[J]. The Annals of Applied Statistics, 2010: 645-662.
[88]	KLEINBERG J. Bursty and hierarchical structure in streams[J]. Data Mining and Knowledge Discovery, 2003, 7(4):373-397. DOI URL
[89]	CHEN W, FANG W, HU G, et al. On the hyperbolicity of small-world and treelike random graphs[J]. Internet Math-ematics, 2013, 9(4):434-491.
[90]	GANEA O E, BÉCIGNEUL G, HOFMANN T. Hyperbolic neural networks[J]. arXiv:1805.09112, 2018.
[91]	ZHU D Y, CUI P, WANG D X, et al. Deep variational network embedding in Wasserstein space[C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, London, Aug 19-23, 2018. New York: ACM, 2018: 2827-2836.
[92]	SUN L, ZHANG Z B, ZHANG J W, et al. Hyperbolic variational graph neural network for modeling dynamic graphs[C]// Proceedings of the 35th AAAI Conference on Artificial Intelligence, the 33rd Conference on Innovative Applications of Artificial Intelligence, the 11th Symposium on Educational Advances in Artificial Intelligence, Virtual Event, Feb 2-9, 2021. Menlo Park: AAAI, 2021: 4375-4383.
[93]	HAMMOND D K, VANDERGHEYNST P, GRIBONVAL R. Wavelets on graphs via spectral graph theory[J]. Applied and Computational Harmonic Analysis, 2011, 30(2):129-150. DOI URL
[94]	DEFFERRARD M, BRESSON X, VANDERGHEYNST P. Convolutional neural networks on graphs with fast localized spectral filtering[J]. arXiv:1606.09375, 2016.
[95]	VELIČKOVIĆ P, CUCURULL G, CASANOVA A, et al. Graph attention networks[J]. arXiv:1710.10903, 2017.
[96]	CHAUDHARI S, MITHAL V, POLATKAN G, et al. An attentive survey of attention models[J]. arXiv:1904.02874, 2019.
[97]	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[J]. arXiv:1706.03762, 2017.
[98]	XU K, HU W, LESKOVEC J, et al. How powerful are graph neural networks?[J]. arXiv:1810.00826, 2018.
[99]	LEMAN A A, WEISFEILER B. A reduction of a graph to a canonical form and an algebra arising during this reduction[J]. Nauchno-Technicheskaya Informatsiya, 1968, 2(9):12-16.
[100]	WANYAN T, ZHANG C, AZAD A, et al. Attribute2vec: deep network embedding through multi-filtering GCN[J]. arXiv:2004.01375, 2020.
[101]	WU F, SOUZA A H, ZHANG T Y, et al. Simplifying graph convolutional networks[C]// Proceedings of the 36th International Conference on Machine Learning, Long Beach, Jun 9-15, 2019: 6861-6871.
[102]	HU F Y, ZHU Y Q, WU S, et al. Graphair: graph rep-resentation learning with neighborhood aggregation and interaction[J]. Pattern Recognition, 2021, 112:107745. DOI URL
[103]	HUANG J, SHEN H, HOU L, et al. SDGNN: learning node representation for signed directed networks[J]. arXiv:2101.02390, 2021.
[104]	LESKOVEC J, HUTTENLOCHER D, KLEINBERG J M. Predicting positive and negative links in online social networks[C]// Proceedings of the 19th International Con-ference on World Wide Web, Raleigh, Apr 26-30, 2010. New York: ACM, 2010: 641-650.
[105]	LESKOVEC J, HUTTENLOCHER D P, KLEINBERG J M. Signed networks in social media[C]// Proceedings of the 28th International Conference on Human Factors in Computing Systems, Atlanta, Apr 10-15, 2010. New York:ACM, 2010: 1361-1370.
[106]	TRIVEDI R, FARAJTABAR M, BISWAL P, et al. Dyrep: learning representations over dynamic graphs[C]// Proceedings of the 2019 International Conference on Learning Repres-entations, 2019.
[107]	ZHANG J, SHI X, XIE J, et al. GaAN: gated attention networks for learning on large and spatiotemporal graphs[J]. arXiv:1803.07294, 2018.
[108]	SANKAR A, WU Y H, GOU L, et al. DySAT: deep neural representation learning on dynamic graphs via self-attention networks[C]// Proceedings of the 13th ACM International Conference on Web Search and Data Mining, Houston, Feb 3-7, 2020. New York: ACM, 2020: 519-527.
[109]	GEHRING J, AULI M, GRANGIER D, et al. Convol-utional sequence to sequence learning[C]// Proceedings of the 34th International Conference on Machine Learning, Sydney, Aug 6-11, 2017. New York: ACM, 2017: 1243-1252.
[110]	PAREJA A, DOMENICONI G, CHEN J, et al. EvolveGCN: evolving graph convolutional networks for dynamic graphs[C]// Proceedings of the 34th AAAI Conference on Artificial Intelligence, the 32nd Innovative Applications of Artificial Intelligence Conference, the 10th AAAI Symposium on Educational Advances in Artificial Intelligence, New York, Feb 7-12, 2020. Menlo Park: AAAI, 2020: 5363-5370.
[111]	MA Y, GUO Z Y, REN Z C, et al. Streaming graph neural networks[C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2020: 719-728.
[112]	FATHY A, LI K. TemporalGAT: attention-based dynamic graph representation learning[C]// LNCS 12084: Proceedings of the 24th Pacific-Asia Conference on Knowledge Dis-covery and Data Mining, Singapore, May 11-14, 2020. Cham: Springer, 2020: 413-423.
[113]	BAI S J, KOLTER J Z, KOLTUN V. An empirical evalu-ation of generic convolutional and recurrent networks for sequence modeling[J]. arXiv:1803.01271, 2018.
[114]	VAN DEN OORD A, DIELEMAN S, ZEN H, et al. Wavenet: a generative model for raw audio[J]. arXiv:1609.03499, 2016.
[115]	SANKAR A, WU Y, GOU L, et al. Dynamic graph repre-sentation learning via self-attention networks[J]. arXiv:1812.09430, 2018.
[116]	TANG J, QU M, WANG M Z, et al. LINE: large-scale information network embedding[C]// Proceedings of the 24th International Conference on World Wide Web, Florence, May 18-22, 2015. New York: ACM, 2015: 1067-1077.
[117]	TU K, CUI P, WANG X, et al. Deep recursive network embedding with regular equivalence[C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, London, Aug 19-23, 2018. New York: ACM, 2018: 2357-2366.
[118]	PAGE L, BRIN S, MOTWANI R, et al. The PageRank citation ranking: bringing order to the Web[R]. Stanford InfoLab, 1999.
[119]	YING C, CAI T, LUO S, et al. Do transformers really perform bad for graph representation?[J]. arXiv:2106.05234, 2021.
[120]	ZUO Y, LIU G N, LIN H, et al. Embedding temporal network via neighborhood formation[C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, London, Aug 19-23, 2018. New York: ACM, 2018: 2857-2866.
[121]	HAWKES A G. Spectral of some self-exciting and mutually exciting point processes[J]. Biometrika, 1971, 58(1):83-90. DOI URL
[122]	ZHOU L K, YANG Y, REN X, et al. Dynamic network embedding by modeling triadic closure process[C]// Pro-ceedings of the 32nd AAAI Conference on Artificial Inte-lligence, the 30th Innovative Applications of Artificial Intelligence, and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence, New Orleans, Feb 2-7, 2018. Menlo Park: AAAI, 2018: 571-578.
[123]	COLEMAN J S. Foundations of social theory[M]. Cam-bridge: Harvard University Press, 1994.
[124]	HUANG H, TANG J, LIU L, et al. Triadic closure pattern analysis and prediction in social networks[J]. IEEE Transactions on Knowledge and Data Engineering, 2015, 27(12):3374-3389. DOI URL
[125]	LU Y F, WANG X, SHI C, et al. Temporal network embe-dding with micro-and macro-dynamics[C]// Proceedings of the 28th ACM International Conference on Information and Knowledge Management, Beijing, Nov 3-7, 2019. New York: ACM, 2019: 469-478.
[126]	WANG Y, CHANG Y Y, LIU Y, et al. Inductive repres-entation learning in temporal networks via causal anon-ymous walks[J]. arXiv:2101.05974, 2021.
[127]	MICALI S, ZHU Z A. Reconstructing Markov processes from independent and anonymous experiments[J]. Discrete Applied Mathematics, 2016, 200:108-122. DOI URL
[128]	AHMED N K, NEVILLE J, ROSSI R A, et al. Efficient graphlet counting for large networks[C]// Proceedings of the 2015 IEEE International Conference on Data Mining, Atlantic City, Nov 14-17, 2015. Washington: IEEE Computer Society, 2015: 1-10.
[129]	PARANJAPE A, BENSON A R, LESKOVEC J. Motifs in temporal networks[C]// Proceedings of the 10th ACM International Conference on Web Search and Data Mining, Cambridge, Feb 6-10, 2017. New York: ACM, 2017: 601-610.
[130]	HORNIK K, STINCHCOMBE M B, WHITE H. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks[J]. Neural Networks, 1990, 3(5):551-560. DOI URL
[131]	ZAFARANI R, LIU H. Social computing data repository[M]. Tempe: Arizona State University, 2009.
[132]	TANG L, LIU H. Scalable learning of collective behavior based on sparse social dimensions[C]// Proceedings of the 18th ACM Conference on Information and Knowledge Management, Hong Kong, China, Nov 2-6, 2009. New York: ACM, 2009: 1107-1116.
[133]	YANG C, LIU Z Y, ZHAO D L, et al. Network repres-entation learning with rich text information[C]// Procee-dings of the 24th International Joint Conference on Artificial Intelligence, Buenos Aires, Jul 25-31, 2015. Menlo Park:AAAI, 2015: 2111-2117.
[134]	SEN P, NAMATA G, BILGIC M, et al. Collective classi-fication in network data[J]. AI Magazine, 2008, 29(3):93.
[135]	ZENG H Q, ZHOU H K, SRIVASTAVA A, et al. Graphsaint: graph sampling based inductive learning method[J]. arXiv:1907.04931, 2019.
[136]	TANG J L, GAO H J, LIU H. mTrust: discerning multi-faceted trust in a connected world[C]// Proceedings of the 5th International Conference on Web Search and Data Mining, Seattle, Feb 8-12, 2012. New York: ACM, 2012: 93-102.
[137]	GEHRKE J, GINSPARG P, KLEINBERG J M. Overview of the 2003 KDD Cup[J]. SIGKDD Explorations, 2003, 5(2):149-151. DOI URL
[138]	LESKOVEC J, KREVL A. SNAP datasets: Stanford large network dataset collection[EB/OL]. [2021-02-10]. http://snap.stanford.edu/data/.
[139]	KLIMT B, YANG Y M. The enron corpus: a new dataset for email classification research[C]// LNCS 3201: Proceedings of the 15th European Conference on Machine Learning, Pisa, Sep 20-24, 2004. Berlin, Heidelberg: Springer, 2004: 217-226.
[140]	PANZARASA P, OPSAHL T, CARLEY K M. Patterns and dynamics of users’ behavior and interaction: network analysis of an online community[J]. Journal of the American Society for Information Science and Technology, 2009, 60(5):911-932. DOI URL
[141]	KUMARAN G, ALLAN J. Adapting information retri-eval systems to user queries[J]. Information Processing & Management, 2008, 44(6):1838-1862. DOI URL
[142]	HOSMER D W, LEMESHOW S, STURDIVANT R X. Applied logistic regression[M]. New York: John Wiley & Sons, Inc., 2000.
[143]	PEDREGOSA F, VAROQUAUX G, GRAMFORT A, et al. Scikit-learn: machine learning in Python[J]. Journal of Machine Learning Research, 2011, 12:2825-2830.
[144]	SUYKENS J A K, VANDEWALLE J. Least squares support vector machine classifiers[J]. Neural Processing Letters, 1999, 9(3):293-300. DOI URL
[145]	MCCALLUM A, NIGAM K. A comparison of event models for Naive Bayes text classification[C]// Procee-dings of the AAAI-98 Workshop on Learning for Text Categorization, Madison, Jul 26-27, 1998. Menlo Park: AAAI, 1998: 41-48.
[146]	VON LUXBURG U. A tutorial on spectral clustering[J]. Statistics and Computing, 2007, 17(4):395-416. DOI URL
[147]	SHI J B, MALIK J. Normalized cuts and image seg-mentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8):888-905. DOI URL
[148]	MACQUEEN J. Some methods for classification and analysis of multivariate observations[C]// Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability, Berkeley, Dec 27, 1965-Jan 7, 1966. Berkeley: University of California Press, 1966: 281-297.
[149]	CAI D, HE X F, HAN J W, et al. Graph regularized nonnegative matrix factorization for data representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(8):1548-1560. DOI URL
[150]	MANZOOR E A, MILAJERDI S, AKOGLU L. Fast memory-efficient anomaly detection in streaming heterogeneous graphs[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, Aug 13-17, 2016. New York: ACM, 2016: 1035-1044.
[151]	RANSHOUS S, HARENBERG S, SHARMA K, et al. A scalable approach for outlier detection in edge streams using sketch-based approximations[C]// Proceedings of the 2016 SIAM International Conference on Data Mining, Miami, May 5-7, 2016. Philadelphia: SIAM, 2016: 189-197.
[152]	TANG J, LIU J Z, ZHANG M, et al. Visualizing large-scale and high-dimensional data[C]// Proceedings of the 25th International Conference on World Wide Web, Mon-treal, Apr 11-15, 2016. New York: ACM, 2016: 287-297.
[153]	YUAN L N, WANG Y, CHENG X G, et al. Semi- AttentionAE: an integrated model for graph representation learning[J]. IEEE Access, 2021, 9:80787-80796. DOI URL
[154]	HU W, FEY M, ZITNIK M, et al. Open graph benchmark: datasets for machine learning on graphs[J]. arXiv:2005.00687, 2020
[155]	ZHAO J N, WANG X, SHI C, et al. Heterogeneous graph structure learning for graph neural networks[C]// Proceedings of the 35th AAAI Conference on Artificial Intelligence, 33rd Conference on Innovative Applications of Artificial Intelligence, the 11th Symposium on Educational Adv-ances in Artificial Intelligence, Virtual Event, Feb 2-9, 2021. Menlo Park: AAAI, 2021: 4697-4705.
[156]	VAN DYK D A, MENG X L. The art of data augmentation[J]. Journal of Computational and Graphical Statistics, 2001, 10(1):1-50. DOI URL
[157]	VERMA V, QU M, KAWAGUCHI K, et al. GraphMix: improved training of GNNs for semi-supervised learning[J]. arXiv:1909.11715, 2019.

图嵌入模型综述

Graph Embedding Models: A Survey

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 35

参考文献 157

相关文章 12

编辑推荐

Metrics

[1]	黄思远, 赵宇海, 梁燚铭. 融合图嵌入和注意力机制的代码搜索[J]. 计算机科学与探索, 2022, 16(4): 844-854.
[2]	蒋光峰, 胡鹏程, 叶桦, 仰燕兰. 基于重构误差的同构图分类模型[J]. 计算机科学与探索, 2022, 16(1): 185-193.
[3]	王晓东, 赵一宁, 肖海力, 王小宁, 迟学斌. 使用GNN与RNN实现用户行为分析[J]. 计算机科学与探索, 2021, 15(5): 838-847.
[4]	赵雪莉, 卢光跃, 吕少卿, 张潘. 结合属性信息的二分网络表示学习[J]. 计算机科学与探索, 2021, 15(3): 495-505.
[5]	李鹏辉, 翟正利, 冯舒. 图对抗防御研究进展[J]. 计算机科学与探索, 2021, 15(12): 2292-2303.
[6]	刘国庆，卢桂馥，周胜，宣东东，曹阿龙. 非负低秩图嵌入算法[J]. 计算机科学与探索, 2020, 14(3): 502-512.
[7]	许磊，黄玲，王昌栋. 保持Motif结构的网络表示学习[J]. 计算机科学与探索, 2019, 13(8): 1261-1271.
[8]	张昱，高克宁，陈默，于戈. 融合网络结构和节点属性的链接预测方法[J]. 计算机科学与探索, 2019, 13(7): 1094-1101.
[9]	杨晓翠，宋甲秀，张曦煌. 基于网络表示学习的链路预测算法[J]. 计算机科学与探索, 2019, 13(5): 812-821.
[10]	舒敏，刘华文，郑忠龙，徐晓丹. 结合局部敏感哈希和随机游走的异常检测算法[J]. 计算机科学与探索, 2018, 12(12): 1950-1960.
[11]	褚晶辉，罗薇，吕卫. 多图嵌入表示在人体运动模式识别中的应用[J]. 计算机科学与探索, 2017, 11(6): 941-949.
[12]	刘恒，寇月，申德荣，王泰明，于戈. 基于随机游走路径的分布式SimRank算法[J]. 计算机科学与探索, 2014, 8(12): 1422-1431.