FLGAI: a unified network embedding framework integrating multi-scale network structures and node attribute information
- PDF / 1,558,574 Bytes
- 14 Pages / 595.276 x 790.866 pts Page_size
- 27 Downloads / 280 Views
FLGAI: a unified network embedding framework integrating multi-scale network structures and node attribute information Yu Pan 1 & Guyu Hu 1 & Junyang Qiu 2 & Yanyan Zhang 1 & Shuaihui Wang 1 & Dongsheng Shao 1 & Zhisong Pan 1
# Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Network embedding is an effective method aiming to learn the low-dimensional vector representation of nodes in networks, which has been widely used in various network analytic tasks such as node classification, node clustering, and link prediction. The objective of network embedding is to capture the structural information and inherent characteristics of the network as much as possible in the low-dimensional vector representation. However, the majority of the existing network embedding methods merely exploited the microscopic proximity of the network structure to learn the node representation, which tend to generate suboptimal network representation. In this paper, we propose a novel nonnegative matrix factorization (NMF) based network representation learning framework called FLGAI, which jointly integrates the local network structure, global network structure, and attribute information to learn the network representation. First, we employ the first-order proximity and second-order proximity jointly to preserve the local network structure. Then, the community structure is introduced to preserve the global network structure. Third, we exploit the node attribute information to capture the node characteristics. To preserve the structural information and the network node attributes simultaneously, we formulate their consensus relationships and optimize them jointly in a unified NMF framework to derive the final network representation. To evaluate the effectiveness of our model, we conduct extensive experiments on six real-world datasets and the empirical results demonstrate the superior performance of the proposed method over the state-of-the-art approaches in both node classification and node clustering tasks. Keywords Network embedding . Network representation learning . Nonnegative matrix factorization . Data mining . Machine learning
1 Introduction Information networks are becoming ubiquitous in the realworld and analyzing these networks provides an insight into the social life [1, 2]. Effective analysis of the network relies heavily on informative network representation while the network analysis can be facilitated better with an appropriate embedding of the network [3]. Therefore, how to learn the desired network representation is one of the fundamental problems in network analysis. After embedding the nodes of network into low-dimensional vectors, many network mining tasks can be directly conducted in the low-dimensional space,
* Zhisong Pan [email protected] 1
Institute of Command and Control Engineering, Army Engineering University, Nanjing 210007, China
2
School of Information Technology, Deakin University, Geelong, Victoria 3216, Australia
such as node classification [4, 5], link prediction [6, 7], v
Data Loading...
