## Chapter2: Graph Representation Learning

###
Peng Cui, Tsinghua University, cuip@tsinghua.edu.cn

Lingfei Wu, Pinterest, lwu@email.wm.edu

Jian Pei, Duke 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.