Deep Learning on Graphs

  

Introduction

Cover of English Version 

This book covers comprehensive contents in developing deep learning techniques for graph structured data with a specific focus on Graph Neural Networks (GNNs). The foundation of the GNN models are introduced in detail including the two main building operations: graph filtering and pooling operations. We then discuss the robustness and scalability of the GNNs, which are extremely important for utilizing GNNs for real-world applications. To enable deep learning techniques to advance more graph tasks under wider settings, we introduce numerous deep graph models beyond GNNs. We also present the most representative applications of GNNs in different areas such as Natural Language Processing, Computer Vision, Data Mining and Healthcare. The book is also self-contained, we include chapters for introducing some basics on graphs and also on deep learning. We conclude the book with recent advances of GNNs in both methods and applications.

The pre-publication verison of the book is released! Subscribe to keep updated!

The Chinese version is officially published.

Authors

Contents

This material will be published by Cambridge University Press as Deep Learning on Graphs by Yao Ma and Jiliang Tang. This pre-publication version is free to view and download for personal use only. Not for re-distribution, re-sale or use in derivative works. © Yao Ma and Jiliang Tang 2020

The Entire Book [preprint]

Table of Contents [ English Version] [Chinese Version]

Introduction

PART 1 Foundations

PART 2 Methods

PART 3 Applications

PART 4 Advances

Bibliography [preprint]

Index [preprint]

Chinese Version

中文版即将正式发售,现已在京东开启预售(预售链接)。

Cover of Chinese Version 

Comments and Feedbacks

Any comments and feedback are welcomed and appreciated! Please send your comments and feedback to mayao4 at msu dot edu

Citing the Book

To cite the book, please use the followng bibtex entry:

@book{ma2020deep,
title={Deep Learning on Graphs},
author={Yao Ma and Jiliang Tang},
publisher={Cambridge University Press},
year={2020}
}