Graph Neural Networks

Foundations, Frontiers, and Applications


Lingfei Wu, Pinterest
Peng Cui, Tsinghua University
Jian Pei, Duke University
Liang Zhao, Emory University

Introduction


The field of graph neural networks (GNNs) has seen rapid and incredible strides over the recent years. Graph neural networks, also known as deep learning on graphs, graph representation learning, or geometric deep learning have become one of the fastest-growing research topics in machine learning, especially deep learning. This wave of research at the intersection of graph theory and deep learning has also influenced other fields of science, including recommendation systems, computer vision, natural language processing, inductive logic programming, program synthesis, software mining, automated planning, cybersecurity, and intelligent transportation.

Although graph neural networks have achieved remarkable attention, it still faces many challenges when applying them into other domains, from the theoretical understanding of methods to the scalability and interpretability in a real system, and from the soundness of the methodology to the empirical performance in an application. However, as the field rapidly grows, it has been extremely challenging to gain a global perspective of the developments of GNNs.


Therefore, we feel the urgency to bridge the above gap and have a comprehensive book on this fast-growing yet challenging topic, which can benefit a broad audience including advanced undergraduate and graduate students, postdoctoral researchers, lecturers, and industrial practitioners.

This book is intended to cover a broad range of topics in graph neural networks, from the foundations to the frontiers, and from the methodologies to the applications. Our book is dedicated to introducing the fundamental concepts and algorithms of GNNs, new research frontiers of GNNs, and broad and emerging applications with GNNs.


The English version of the book is available for purchase on Amazon and Springer.

简介


近年来，图神经网络（GNN）取得了快速、令人难以置信的进展。图神经网络又称为图深度学习、图表征学习（图表示学习）或几何深度学习，是机器学习特别是深度学习领域增长最快的研究课题。图论和深度学习交叉领域的这波研究浪潮也影响了其他科学领域，包括推荐系统、计算机视觉、自然语言处理、归纳逻辑编程、程序合成、软件挖掘、自动规划、网络安全和智能交通等。

尽管图神经网络已经取得令人瞩目的成就，但我们在将其应用于其他领域时仍面临着许多挑战，包括从方法的理论理解到实际系统中的可拓展性和可解释性，从方法的合理性到应用中的经验表现，等等。然而，随着图神经网络的快速发展，要获得图神经网络发展的全局视角时非常具有挑战性的。因此，我们感到迫切需要弥合上述差距，并就这一快速增长但具有挑战性的主题编写一本全面的书，这可以使广大读者收益，包括高年级本科生和研究生、博士后研究人员、讲师及相关的从业人员。

本书涵盖图神经网络的广泛主题，从基础到前沿，从方法到应用，涉及从方法论到应用场景方方面面的内容。我们致力于介绍图神经网络的基本概念和算法、研究前沿以及广泛和新兴的应用。


The Chinese version is available for pre-order now (50% off) at JD.com now!

Review

“The first comprehensive book covering the full spectrum of a young, fast-growing research field, graph neural networks (GNNs), written by authoritative authors!”
---Jiawei Han (Michael Aiken Chair Professor at University of Illinois at Urbana-Champaign, ACM Fellow and IEEE Fellow)

“This book presents a comprehensive and timely survey on graph representation learning. Edited and contributed by the best group of experts in this area, this book is a must-read for students, researchers and pratictioners who want to learn anything about Graph Neural Networks.”
---Heung-Yeung ”Harry” Shum (Former Executive Vice President for Technology and Research at Microsoft Research, ACM Fellow, IEEE Fellow, FREng)

“As the new frontier of deep learning, Graph Neural Networks offer great potential to combine probabilistic learning and symbolic reasoning, and bridge knowledge-driven and data-driven paradigms, nurturing the development of third-generation AI. This book provides a comprehensive and insightful introduction to GNN, ranging from foundations to frontiers, from algorithms to applications. It is a valuable resource for any scientist, engineer and student who wants to get into this exciting field.”
---Bo Zhang (Member of Chinese Academy of Science, Professor at Tsinghua University)

“Graph Neural Networks are one of the hottest areas of machine learning and this book is a wonderful in-depth resource covering a broad range of topics and applications of graph representation learning.”
---Jure Leskovec (Associate Professor at Stanford University, and investigator at Chan Zuckerberg Biohub)

“Graph Neural Networks are an emerging machine learning model that is already taking the scientific and industrial world by storm. The time is perfect to get in on the action – and this book is a great resource for newcomers and seasoned practitioners alike! Its chapters are very carefully written by many of the thought leaders at the forefront of the area.”
---Petar Velickovic (Senior Research Scientist, DeepMind)

Access

Chapters

Chapter1: Representation Learning

Liang Zhao, Lingfei Wu, Peng Cui, Jian Pei

Chapter2: Graph Representation Learning

Peng Cui, Lingfei Wu, Jian Pei, Liang Zhao, Xiao Wang

Chapter3: Graph Neural Networks

Lingfei Wu, Peng Cui, Jian Pei, Liang Zhao, Le Song

Chapter4: Graph Neural Networks for Node Classification

Jian Tang, Renjie Liao

Chapter5: The Expressive Power of Graph Neural Networks

Pan Li, Jure Leskovec

Chapter6: Graph Neural Networks: Scalability

Hehuan Ma, Yu Rong, Junzhou Huang

Chapter7: Interpretability in Graph Neural Networks

Ninghao Liu, Qizhang Feng, Xia Hu

Chapter8: Graph Neural Networks: Adversarial Robustness

Stephan Günnemann

Chapter9: Graph Neural Networks: Graph Classification

Christopher Morris

Chapter10: Graph Neural Networks: Link Prediction

Muhan Zhang

Chapter11: Graph Neural Networks: Graph Generation

Renjie Liao

Chapter12: Graph Neural Networks: Graph Transformation

Xiaojie Guo, Shiyu Wang, Liang Zhao

Chapter13: Graph Neural Networks: Graph Matching

Xiang Ling, Lingfei Wu, Chunming Wu, Shouling Ji

Chapter14: Graph Neural Networks: Graph Structure Learning

Yu Chen, Lingfei Wu

Chapter15: Dynamic Graph Neural Networks

Seyed Mehran Kazemi

Chapter16: Heterogeneous Graph Neural Networks

Chuan Shi

Chapter17: Graph Neural Networks: AutoML

Kaixiong Zhou, Zirui Liu, Keyu Duan, Xia Hu

Chapter18: Graph Neural Networks: Self-supervised Learning

Yu Wang, Wei Jin, Tyler Derr

Chapter19: Graph Neural Networks in Modern Recommender Systems

Yunfei Chu, Jiangchao Yao, Chang Zhou, Hongxia Yang

Chapter20: Graph Neural Networks in Computer Vision

Siliang Tang, Wenqiao Zhang, Zongshen Mu, Kai Shen, Juncheng Li, Jiacheng Li, Lingfei Wu

Chapter21: Graph Neural Networks in Natural Language Processing

Bang Liu, Lingfei Wu

Chapter22: Graph Neural Networks in Program Analysis

Miltiadis Allamanis

Chapter23: Graph Neural Networks in Software Mining

Collin McMillan

Chapter24: GNN-based Biomedical Knowledge Graph Mining in Drug Development

Chang Su, Yu Hou, Fei Wang

Chapter25: Graph Neural Networks in Predicting Protein Function and Interactions

Anowarul Kabir, Amarda Shehu

Chapter26: Graph Neural Networks in Anomaly Detection

Shen Wang, Philip S. Yu

Chapter27: Graph Neural Networks in Urban Intelligence

Yanhua Li, Xun Zhou, Menghai Pan

Copyrights and Citation

This book is a pre-publication draft of the book that will be published by Springer. The publishers have generously agreed to allow the public hosting of the pre-publication draft, which does not include the publisher's formatting or revisions. The book should be cited as follows:

@book{GNNBook2022,
author = "Wu, Lingfei and Cui, Peng and Pei, Jian and Zhao, Liang",
title = "Graph Neural Networks: Foundations, Frontiers, and Applications",
publisher = "Springer Singapore",
address = "Singapore",
pages = "725",
year = "2022",
}

L. Wu, P. Cui, J. Pei, and L. Zhao. Graph Neural Networks: Foundations, Frontiers, and Applications. Springer, Singapore, 2022
All copyrights held by the authors and publishers extend to the pre-publication drafts.

Feedbacks

Feedback, typo corrections, and comments are welcome and should be sent to Dr. Lingfei Wu at teddy.lfwu@gmail.com with [GNN BOOK] in the subject line.