摘要
传统网络表示学习算法大多依赖于节点视角下的随机游走获取网络局部采样序列,再通过最大化相邻节点的共现概率将网络中的节点表示成低维向量.本文在真实网络上的经验分析表明,对节点和边两种视角分别进行随机游走会产生具有不同节点分布的采样序列,进而得到不同的社区划分.为此,本文提出了一种基于双视角的耦合表示学习算法DPBCNE.该方法基于边视角进行随机游走以获得不同于节点视角的采样结果,再融合基于节点视角下的节点采样序列进行耦合训练,以学习节点和边的表示.实验结果表明,相较于现有的网络表示学习算法,DPBCNE能更好地保留网络拓扑结构信息,并在下游分类和预测任务中获得更好的效果.
Traditional network embedding approaches rely heavily on random walk in a node perspective to get the local sampling sequence of networks and then maximize the co-occurrence probability between adjacent nodes to represent nodes as low-dimensional vectors.The empirical analysis of this study on a real-world network shows that random walk in node and link perspectives can respectively produce network sampling results with different node frequency distributions,resulting in various partitions of the network.To this end,this study proposes an approach to Dual Perspective Based Coupled Network Embedding(DPBCNE).DBPCNE gets the network sampling sequences by random walk in a link perspective and then combines node sequences sampled in a node perspective for coupled training.Experiments show that compared with other network embedding approaches,this approach can well preserve network structures and improve the effectiveness of network embedding for the downstream classification and prediction tasks.
作者
倪琦瑄
张霞
卜湛
NI Qi-Xuan;ZHANG Xia;BU Zhan(College of Information Engineering,Nanjing University of Finance and Economics,Nanjing 210003,China;College of Artificial Intelligence and Information Technology,Nanjing University of Chinese Medicine,Nanjing 210023,China;Jiangsu Provincial Key Laboratory of E-Business,Nanjing University of Finance and Economics,Nanjing 210003,China)
出处
《计算机系统应用》
2021年第9期247-255,共9页
Computer Systems & Applications
基金
国家重点研发计划(2019YFB1405000)
国家自然科学基金(71871109)。
关键词
双视角
网络表示学习
随机游走
边图
dual perspective
network embedding
random walk
line graph
