## Chapter4: Graph Neural Networks for Node Classification

###
Jian Tang, Mila-Quebec AI Institute, jian.tange@hec.ca

Renjie Liao, University of Toronto, rjliao@cs.toronto.edu

## Abstract

'Graph Neural Networks are neural architectures specifically designed for graph-structured data, which have been receiving increasing attention recently and applied to different domains and applications. In this chapter, we focus on a fundamental task on graphs: node classification.We will give a detailed definition of node classification and also introduce some classical approaches such as label propagation. Afterwards, we will introduce a few representative architectures of graph neural networks for node classification. We will further point out the main difficulty— the oversmoothing problem—of training deep graph neural networks and present some latest advancement along this direction such as continuous graph neural networks.'

## Contents

- Background and Problem Definition
- Supervised Graph Neural Networks
- General Framework of GNNs
- Graph Convoluntional Networks
- Graph Attention Networks
- Neural Message Passing Networks
- Continuous Graph Neural Networks
- Multi-Scale Spectral Graph Convolutional Networks
- Unsupervised Graph Neural Networks
- Variational Graph Auto-Encoders
- Deep Graph Infomax
- Over-smoothing Problem
- Summary

## Citation

@incollection{GNNBook-ch4-tang,

author = "Tang, Jian and Liao, Renjie",

editor = "Wu, Lingfei and Cui, Peng and Pei, Jian and Zhao, Liang",

title = "Graph Neural Networks for Node Classification",

booktitle = "Graph Neural Networks: Foundations, Frontiers, and Applications",

year = "2022",

publisher = "Springer Singapore",

address = "Singapore",

pages = "41--61",

}

J. Tang and R. Liao, “Graph neural networks for node classification,” in Graph Neural Networks: Foundations, Frontiers, and Applications, L. Wu, P. Cui, J. Pei, and L. Zhao, Eds. Singapore: Springer Singapore, 2022, pp. 41–61.