Abstract

Social network analysis focuses on extraction of various network properties and facilitates many applications like link prediction and community detection. As one of those popular and promising analytical approaches, network embedding aims to represent the network in a low-dimensional space with preservation of the network's structure and inherent properties. Existing network embedding methods are mainly targeted at network's microscopic structure, particularly at first-order and second-order proximities of nodes. However, the demand of scalable community structural information preservation is ignored. In this paper, we propose a novel Seed-Expansion sampling based Network Embedding model (SENE) to capture mesoscale community information into our learned vectors. We also present an improved network sampling algorithm based on XS strategy to capture node sequences that contain more information. We then feed the sampled node context to Skip-Gram model. Extensive experimental results on several sorts of social networks demonstrate the superior performance of the proposed method over the state-of-the-arts.

Full Text

Published Version

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.