Exploiting centrality information with graph convolutions for network representation learning

Hongxu Chen, Hongzhi Yin, Tong Chen, Quoc Viet Hung Nguyen, Wen Chih Peng, Xue Li

研究成果: Conference contribution同行評審

57 引文 斯高帕斯(Scopus)

摘要

Network embedding has been proven effective to learn low-dimensional vector representations for network vertices, and recently received a tremendous amount of research attention. However, most of existing methods for network embedding merely focus on preserving the first and second order proximities between nodes, and the important properties of node centrality are neglected. Various centrality measures such as Degree, Closeness, Betweenness, Eigenvector and PageRank centralities have been designed to measure the importance of individual nodes. In this paper, we focus on a novel yet unsolved problem that aims to learn low-dimensional continuous nodes representations that not only preserve the network structure, but also keep the centrality information. We propose a generalizable model, namely GraphCSC, that utilizes both linkage information and centrality information to learn low-dimensional vector representations for network vertices. The learned embeddings by GraphCSC are able to preserve different centrality information of nodes. In addition, we further propose GraphCSC-M, a more comprehensive model that can preserve different centrality information simultaneously through learning multiple centrality-specific embeddings, and a novel attentive multi-view learning approach is developed to compress multiple embeddings of one node into a compact vector representation. Extensive experiments have been conducted to demonstrate that our model is able to preserve different centrality information of nodes, and achieves better performance on several benchmark tasks compared with recent state-of-the-art network embedding methods.

原文English
主出版物標題Proceedings - 2019 IEEE 35th International Conference on Data Engineering, ICDE 2019
發行者IEEE Computer Society
頁面590-601
頁數12
ISBN(電子)9781538674741
DOIs
出版狀態Published - 4月 2019
事件35th IEEE International Conference on Data Engineering, ICDE 2019 - Macau, China
持續時間: 8 4月 201911 4月 2019

出版系列

名字Proceedings - International Conference on Data Engineering
2019-April
ISSN(列印)1084-4627

Conference

Conference35th IEEE International Conference on Data Engineering, ICDE 2019
國家/地區China
城市Macau
期間8/04/1911/04/19

指紋

深入研究「Exploiting centrality information with graph convolutions for network representation learning」主題。共同形成了獨特的指紋。

引用此