You can view the full text of this article for free using the link below.

Title: A hierarchical network embedding method based on network partitioning

Authors: Xiankun Zhang; Yunbin Ma; Xuexiong Luo; Junlong Kang

Addresses: College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin 300457, China ' College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin 300457, China ' College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin 300457, China ' College of Artificial Intelligence, Tianjin University of Science and Technology, Tianjin 300457, China

Abstract: In order to analyse the real-world information network more effectively, we propose a hierarchical network embedding method based on network partitioning, NPHNE. NPHNE is a nested algorithm that can be combined with existing baseline algorithms to enhance their representation. NPHNE consists of two parts: graph abstracting and embedding propagation. The process of NPHNE is as follows: Firstly, modularity is used to pre-determine the network partition, the purpose is to constrain the maximum number of levels. Then, based on the hybrid collapsing method, a series of abstract graphs with successively smaller scales are constructed. The representation of the coarsest abstract graph is learned by the existing baseline algorithms. Finally, the representation is propagated and refined level by level from the coarsest abstract graph to the original graph. We evaluate NPHNE on multi-label classification tasks on citation network and social network. The experimental results demonstrate that the maximum performance gains over the baseline algorithm by up to 29.1% Macro-F1 score.

Keywords: hierarchical network embedding; network partitioning; modularity; multi-label classification.

DOI: 10.1504/IJCAT.2021.113653

International Journal of Computer Applications in Technology, 2021 Vol.65 No.1, pp.87 - 95

Received: 21 May 2020
Accepted: 28 Jul 2020

Published online: 06 Mar 2021 *

Full-text access for editors Access for subscribers Free access Comment on this article