A Survey on Embedding Dynamic Graphs

Claudio D. T. Barros

doi:10.1145/3483595

Return

A Survey on Embedding Dynamic Graphs

2021-11-23

Claudio D. T. Barros *

Matheus R. F. Mendonça

Alex Borges Vieira

Artur Ziviani

DOI：10.1145/3483595

Original

Save

Abstract

En 中文

Embedding static graphs in low-dimensional vector spaces plays a key role in network analytics and inference, supporting applications like node classification, link prediction, and graph visualization. However, many realworld networks present dynamic behavior, including topological evolution, feature evolution, and diffusion. Therefore, several methods for embedding dynamic graphs have been proposed to learn network representations over time, facing novel challenges, such as time-domain modeling, temporal features to be captured, and the temporal granularity to be embedded. In this survey, we overview dynamic graph embedding, discussing its fundamentals and the recent advances developed so far. We introduce the formal definition of dynamic graph embedding, focusing on the problem setting and introducing a novel taxonomy for dynamic graph embedding input and output. We further explore different dynamic behaviors that may be encompassed by embeddings, classifying by topological evolution, feature evolution, and processes on networks. Afterward, we describe existing techniques and propose a taxonomy for dynamic graph embedding techniques based on algorithmic approaches, from matrix and tensor factorization to deep learning, random walks, and temporal point processes. We also elucidate main applications, including dynamic link prediction, anomaly detection, and diffusion prediction, and we further state some promising research directions in the area.

Keywords:

Dynamic networks

graph embedding

graph representation learning

dynamic graphs

dynamic graph embedding