Learning network representations

Abstract

In this review I present several representation learning methods, and discuss the latest advancements with emphasis in applications to network science. Representation learning is a set of techniques that has the goal of efficiently mapping data structures into convenient latent spaces. Either for dimensionality reduction or for gaining semantic content, this type of feature embeddings has demonstrated to be useful, for example, for node classification or link prediction tasks, among many other relevant applications to networks. I provide a description of the state-of-the-art of network representation learning as well as a detailed account of the connections with other fields of study such as continuous word embeddings and deep learning architectures. Finally, I provide a broad view of several applications of these techniques to networks in various domains.