Graph Representation Learning: A Survey

TL;DR

This survey reviews recent advances in graph representation learning, discussing techniques, challenges, evaluations, and future directions for converting complex graph data into meaningful low-dimensional embeddings.

Contribution

It provides a comprehensive overview of graph embedding methods, compares their performance, and discusses future research directions in the field.

Findings

State-of-the-art methods vary in performance across datasets

Graph embedding techniques effectively preserve intrinsic graph properties

Future directions include scalable and dynamic graph embeddings

Abstract

Research on graph representation learning has received a lot of attention in recent years since many data in real-world applications come in form of graphs. High-dimensional graph data are often in irregular form, which makes them more difficult to analyze than image/video/audio data defined on regular lattices. Various graph embedding techniques have been developed to convert the raw graph data into a low-dimensional vector representation while preserving the intrinsic graph properties. In this review, we first explain the graph embedding task and its challenges. Next, we review a wide range of graph embedding techniques with insights. Then, we evaluate several state-of-the-art methods against small and large datasets and compare their performance. Finally, potential applications and future directions are presented.