•  
  •  
 

Turkish Journal of Electrical Engineering and Computer Sciences

DOI

10.3906/elk-1807-333

Abstract

High dimensionality of data is a challenging scenario in the current era as the digital transformation of the society is in process. This problem is particularly complex in social networks as in such systems, it is coupled with other challenges such as interdependency of data points and heterogeneity of data sources. To overcome such disadvantages and aid in creation of downstream applications for social network analysis, network embedding techniques have been proposed. These techniques, in themselves, are not important but are the backbone of various network-based applications. Due to the scientific interest in this domain there has been a mushrooming of embedding techniques. It has therefore become crucial to learn the intuitions behind these techniques in order to compare and contrast them. The current analytical study is drawn with the following broad objectives: providing practitioners with understanding of network representative learning mathematical study of state-of-the-art techniques and highlighting the evolution of the literature in this field.

Keywords

Dimensionality reduction, network embedding, latent space

First Page

4768

Last Page

4782

Download

Share

COinS