A Survey on Network Embedding

TLDR

Network embedding maps nodes to low‑dimensional vectors while preserving network structure, and recent advances have accelerated this emerging analysis paradigm. This survey categorizes and reviews current network embedding methods and outlines future research directions. The authors motivate network embedding, review classical graph‑embedding algorithms, then systematically survey a wide range of methods—including structure‑, property‑, side‑information, and advanced information‑preserving variants—along with evaluation techniques, resources, and system‑building frameworks.

Abstract

Network embedding assigns nodes in a network to low-dimensional representations and effectively preserves the network structure. Recently, a significant amount of progresses have been made toward this emerging network analysis paradigm. In this survey, we focus on categorizing and then reviewing the current development on network embedding methods, and point out its future research directions. We first summarize the motivation of network embedding. We discuss the classical graph embedding algorithms and their relationship with network embedding. Afterwards and primarily, we provide a comprehensive overview of a large number of network embedding methods in a systematic manner, covering the structure- and property-preserving network embedding methods, the network embedding methods with side information, and the advanced information preserving network embedding methods. Moreover, several evaluation approaches for network embedding and some useful online resources, including the network data sets and softwares, are reviewed, too. Finally, we discuss the framework of exploiting these network embedding methods to build an effective system and point out some potential future directions.