Learning topological representation for networks via hierarchical sampling

Fu, Guoji; Hou, Chengbin; Yao, Xin

10.1109/IJCNN.2019.8851893

2019-07

IJCNN 2019: International Joint Conference on Neural Networks

2161-4393

978-1-7281-1986-1

2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)

1-8

14-19 July 2019

Budapest, Hungary

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

The topological information is essential for studying the relationship between nodes in a network. Recently, Network Representation Learning (NRL), which projects a network into a low-dimensional vector space, has been shown their advantages in analyzing large-scale networks. However, most existing NRL methods are designed to preserve the local topology of a network and they fail to capture the global topology. To tackle this issue, we propose a new NRL framework, named HSRL, to help existing NRL methods capture both local and global topological information of a network. Specifically, HSRL recursively compresses an input network into a series of smaller networks using a community-awareness compressing strategy. Then, an existing NRL method is used to learn node embeddings for each compressed network. Finally, the node embeddings of the input network are obtained by concatenating the node embeddings resulting from all compressed networks. Empirical studies of link prediction on five real-world datasets demonstrate the advantages of HSRL over state-of-the-art methods.

Networks analysis network topology representation learning

第一

英语

CPCI-S

National Key R&D Program of China[2017YFC0804003]

WOS:000530893801085

Web of Science

Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, 518055, P. R. China

Fu, Guoji,Hou, Chengbin,Yao, Xin. Learning topological representation for networks via hierarchical sampling[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2019:1-8.