Network Representation Learning: From Preprocessing, Feature Extraction to Node Embedding

TL;DR

This survey reviews the principles and techniques of network representation learning for homogeneous networks, introducing a unified framework to compare different node embedding methods and guide future algorithm development.

Contribution

It presents a unified reference framework for node embedding learning, facilitating comparison and understanding of various algorithms in network representation learning.

Findings

Highlights key methods and models at different stages of node embedding

Provides practical guidelines for designing new NRL algorithms

Facilitates comparison of embedding techniques across studies

Abstract

Network representation learning (NRL) advances the conventional graph mining of social networks, knowledge graphs, and complex biomedical and physics information networks. Over dozens of network representation learning algorithms have been reported in the literature. Most of them focus on learning node embeddings for homogeneous networks, but they differ in the specific encoding schemes and specific types of node semantics captured and used for learning node embedding. This survey paper reviews the design principles and the different node embedding techniques for network representation learning over homogeneous networks. To facilitate the comparison of different node embedding algorithms, we introduce a unified reference framework to divide and generalize the node embedding learning process on a given network into preprocessing steps, node feature extraction steps and node embedding model training for a NRL task such as link prediction and node clustering. With this unifying reference framework, we highlight the representative methods, models, and techniques used at different stages of the node embedding model learning process. This survey not only helps researchers and practitioners to gain an in-depth understanding of different network representation learning techniques but also provides practical guidelines for designing and developing the next generation of network representation learning algorithms and systems.