Deep Learning for Learning Graph Representations
This is an incremental survey chapter summarizing existing graph representation techniques for network data analysis.
The paper addresses the challenge of analyzing large-scale network data by introducing graph representation methods that map graphs into low-dimensional vector spaces while preserving structure, though it does not present new experimental results or concrete performance metrics.
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.