Chapter2: Graph Representation Learning

Peng Cui, Tsinghua University, cuip@tsinghua.edu.cn
Lingfei Wu, JD.COM Silicon Valley Research Center, lwu@email.wm.edu
Jian Pei, Simon Fraser University, jpei@cs.sfu.edu
Liang Zhao, Emory University, liang.zhao@emory.edu
Xiao Wang, Beijing University of Posts and Telecommunications, xiaowang@bupt.edu.cn

Abstract

Graph representation learning aims at assigning nodes in a graph to low-dimensional representations and effectively preserving the graph structure. Recently, a significant amount of progresses have been made toward this emerging graph analysis paradigm. In this chapter, we first summarize the motivation of graph representation learning. Afterwards and primarily, we provide a comprehensive overview of a large number of graph representation learning methods in a systematic manner, covering the traditional graph representation learning, modern graph representation learning, and graph neural networks..

Contents

  • Graph Representation Learning: An Introduction
  • Traditional Graph Embedding
  • Modern Graph Embedding
    • Structure-Property Perserving Graph Representation Learning
    • Graph Representation Learning with Side Information
    • Advanced Information Perserving Graph Representation Learning
  • Graph Neural Networks
  • Summary

Citation

@incollection{GNNBook-ch2-cui,
author = "Cui, Peng and Wu, Lingfei and Pei, Jian and Zhao, Liang and Wang, Xiao",
editor = "Wu, Lingfei and Cui, Peng and Pei, Jian and Zhao, Liang",
title = "Graph Representation Learning",
booktitle = "Graph Neural Networks: Foundations, Frontiers, and Applications",
year = "2022",
publisher = "Springer Singapore",
address = "Singapore",
pages = "17--26",
}

P. Cui, L. Wu, J. Pei, L. Zhao, and X. Wang, “Graph representation learning,” in Graph Neural Networks: Foundations, Frontiers, and Applications, L. Wu, P. Cui, J. Pei, and L. Zhao, Eds. Singapore: Springer Singapore, 2022, pp. 17–26.