Deep Learning for Learning Graph Representations

TL;DR

This paper reviews the development of deep learning techniques for graph representation, emphasizing methods that embed graphs into low-dimensional spaces to facilitate analysis and inference.

Contribution

It introduces fundamental concepts and representative models in graph representation learning, highlighting their theoretical importance and practical applications.

Findings

Graph embedding preserves original graph structure.

Deep learning models improve graph analysis efficiency.

Various models demonstrate effectiveness in different tasks.

Abstract

Mining graph data has become a popular research topic in computer science and has been widely studied in both academia and industry given the increasing amount of network data in the recent years. However, the huge amount of network data has posed great challenges for efficient analysis. This motivates the advent of graph representation which maps the graph into a low-dimension vector space, keeping original graph structure and supporting graph inference. The investigation on efficient representation of a graph has profound theoretical significance and important realistic meaning, we therefore introduce some basic ideas in graph representation/network embedding as well as some representative models in this chapter.