Representation Learning on Graphs: Methods and Applications

TL;DR

This paper reviews recent advances in graph representation learning, focusing on methods like matrix factorization, random walks, and neural networks, and discusses their applications and future research directions.

Contribution

It provides a unified framework for understanding various graph embedding techniques and highlights key developments and challenges in the field.

Findings

Deep learning methods improve graph embeddings.

Various algorithms effectively encode node and graph structures.

Applications span drug design to social network analysis.

Abstract

Machine learning on graphs is an important and ubiquitous task with applications ranging from drug design to friendship recommendation in social networks. The primary challenge in this domain is finding a way to represent, or encode, graph structure so that it can be easily exploited by machine learning models. Traditionally, machine learning approaches relied on user-defined heuristics to extract features encoding structural information about a graph (e.g., degree statistics or kernel functions). However, recent years have seen a surge in approaches that automatically learn to encode graph structure into low-dimensional embeddings, using techniques based on deep learning and nonlinear dimensionality reduction. Here we provide a conceptual review of key advancements in this area of representation learning on graphs, including matrix factorization-based methods, random-walk based algorithms, and graph neural networks. We review methods to embed individual nodes as well as approaches to embed entire (sub)graphs. In doing so, we develop a unified framework to describe these recent approaches, and we highlight a number of important applications and directions for future work.