《计算机应用研究》|Application Research of Computers

基于深度自编码的局部增强属性网络表示学习

Locally enhanced attribute network embedding via deep auto-encoder

免费全文下载 (已被下载 次)  
获取PDF全文
作者 陈嶷瑛,张珊珊,柴变芳
机构 河北地质大学 信息工程学院,石家庄 050031
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2020)09-009-2610-05
DOI 10.19734/j.issn.1001-3695.2019.04.0126
摘要 基于深度自编码器的网络表示,可以捕获高度非线性的网络结构,但当链接稀疏时学到的表示不够准确。针对这一问题,提出一种基于深度自编码的局部增强属性网络表示学习模型,以提高表示学习的准确度。该模型首先利用链接与属性特征,采用多个深度自编码器,学习保持网络拓扑结构及属性特征的低维网络表示。之后,基于节点间近邻结构及属性相似性,对学出的低维网络表示进行节点约束,实现网络局部结构增强,达到最大程度保持原始结构信息及属性特征的目的。在五个真实属性网络上的实验结果表明,提出的模型在聚类与分类任务中,效果均优于目前流行的表示学习方法。
关键词 网络表示; 深度自编码器; 属性网络; 局部增强网络表示
基金项目 国家自然科学基金资助项目(61503260)
本文URL http://www.arocmag.com/article/01-2020-09-009.html
英文标题 Locally enhanced attribute network embedding via deep auto-encoder
作者英文名 Chen Yiying, Zhang Shanshan, Chai Bianfang
机构英文名 College of Information Engineering,Hebei GEO University,Shijiazhuang 050031,China
英文摘要 The network embedding method via deep auto-encoder can capture and preserve the structure of highly non-linear network. But when the links are sparse, the representation is not accurate. In order to improve the accuracy, this paper proposed LEANE model. More specifically, this paper firstly used multiple deep auto-encoders to learn a representation of the low-dimensional network where preserved the network topology and semantic information on nodes of networks. Then it introduced a pairwise constraint on the low-dimensional representation according to the similarity between two nodes to enhance local network structures. The pairwise constraint considered both topological neighbor relationship and semantic similarity of nodes. So, the LEANE model can better preserve the original network topology and semantic in-formation. Extensive experiments on five real-world networks demonstrate a superior performance of this method over state-of-the-art methods for embedding.
英文关键词 network embedding; deep auto-encoder; attribute network; locally enhanced network embedding
参考文献 查看稿件参考文献
 
收稿日期 2019/4/24
修回日期 2019/6/18
页码 2610-2614
中图分类号 TP391
文献标志码 A