A hierarchical network embedding method based on network partitioning. (6th March 2021)

• Record Type: Journal Article
• Authors: Zhang, Xiankun; Ma, Yunbin; Luo, Xuexiong; Kang, Junlong
• Is Part Of: International journal of computer applications technology. Volume 65:Number 1(2021)
• Page Start: 87
• Page End: 95
• Publication Date: 2021-03-06
• Subjects: hierarchical network embedding -- network partitioning -- modularity -- multi-label classification; Technology -- Data processing -- Periodicals; 620.00285
• Languages: English
• ISSNs: 0952-8091

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.