Network Representation Learning: From Traditional Feature Learning to Deep Learning

TL;DR

This paper surveys the evolution of network representation learning from traditional methods to deep learning approaches, analyzing their relationships, recent progress, and future challenges in graph data analysis.

Contribution

It provides a comprehensive overview of classical and deep learning-based NRL methods, highlighting recent advancements and open issues in the field.

Findings

Deep learning enhances NRL effectiveness.

Recent methods improve graph embedding quality.

Open issues include scalability and interpretability.

Abstract

Network representation learning (NRL) is an effective graph analytics technique and promotes users to deeply understand the hidden characteristics of graph data. It has been successfully applied in many real-world tasks related to network science, such as social network data processing, biological information processing, and recommender systems. Deep Learning is a powerful tool to learn data features. However, it is non-trivial to generalize deep learning to graph-structured data since it is different from the regular data such as pictures having spatial information and sounds having temporal information. Recently, researchers proposed many deep learning-based methods in the area of NRL. In this survey, we investigate classical NRL from traditional feature learning method to the deep learning-based model, analyze relationships between them, and summarize the latest progress. Finally, we discuss open issues considering NRL and point out the future directions in this field.