.png){kind=icon}
.png){kind=icon}
Return
Rank2vec: Learning node embeddings with local structure and global ranking
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2019.06.045.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Network embedding aims to project each node to a low-dimensional representation while maximally preserving network structure and inherent properties. It is attracting tremendous attention due to its great significance in various network analysis tasks, such as expert finding, relationship prediction, people classification, community identification, etc. However, the existing embedding methods mainly focus on capturing the microscopic structure of the nodes in the network. But they ignore the different global roles played by the nodes, resulting in the limitations in the mesoscopic and macroscopic tasks. To address this problem, we propose a novel network embedding method named Rank2vec. It considers both local structure and global structural roles. Thus it enables the learned representations to preserve both the microscopic and macroscopic information. To evaluate the proposed model, we conduct some extensive experiments on the task of multi-label classification on several real data sets. The experimental results have shown that the Rank2vec achieves significant improvement than state-of-the-art methods. (C) 2019 Elsevier Ltd. All rights reserved.
Keywords:
Network representation
Node embedding
Local structure
Global role
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
7.5
Papers:
2.9W
Citations:
10.2W
Organization
No organization information available