文献类型：期刊文献

英文题名：Graph representation learning with encoding edges

作者：Li, Qi[1];Cao, Zehong[2];Zhong, Jiang[3];Li, Qing[3]

机构：[1]Shaoxing Univ, Dept Comp Sci & Engn, Shaoxing 312000, Peoples R China;[2]Univ Tasmania, Sch Technol Environm & Design, Discipline ICT, Hobart, Tas 7001, Australia;[3]Chongqing Univ, Coll Comp Sci, Chongqing 400044, Peoples R China

年份：2019

卷号：361

起止页码：29

外文期刊名：NEUROCOMPUTING

收录：SCI-EXPANDED(收录号：WOS:000480413200004)、、EI(收录号：20193207273251)、Scopus(收录号：2-s2.0-85070345993)、WOS

基金：This work was supported in part by National Nature Science Foundation of China (No. 61762025), Frontier and Application Foundation Research Program of CQ CSTC (No. cstc2017jcyjAX0340), the Key Industries Common Key Technologies Innovation Projects of CQ CSTC (No. cstc2017zdcy-zdyxx0047), the Fundamental Research Funds for the Central Universities (No. 2018CDYJSY0055), and Graduate Research and Innovation Foundation of Chongqing (No. CYB18058).

语种：英文

外文关键词：Network embedding; Feature learning; Edge representation; Network mining

外文摘要：Network embedding aims at learning the low dimensional representation of nodes. These representations can be widely used for network mining tasks, such as link prediction, anomaly detection, and classification. Recently, a great deal of meaningful research work has been carried out on this emerging network analysis paradigm. The real-world network contains different size clusters because of the edges with different relationship types. These clusters also reflect some features of nodes, which can contribute to the optimization of the feature representation of nodes. However, existing network embedding methods do not distinguish these relationship types. In this paper, we propose an unsupervised network representation learning model that can encode edge relationship information. Firstly, an objective function is defined, which can learn the edge vectors by implicit clustering. Then, a biased random walk is designed to generate a series of node sequences, which are put into Skip-Gram to learn the low dimensional node representations. Extensive experiments are conducted on several network datasets. Compared with the state-of-art baselines, the proposed method is able to achieve favorable and stable results in multi-label classification and link prediction tasks. (C) 2019 Elsevier B.V. All rights reserved.