Graph Representation Learning
- © 2020
- William L. Hamilton 0
McGill University, Canada Mila-Quebec Artificial Intelligence Institute, Canada
You can also search for this author in PubMed Google Scholar
Part of the book series: Synthesis Lectures on Artificial Intelligence and Machine Learning (SLAIML)
6830 Accesses
148 Citations
This is a preview of subscription content, log in via an institution to check access.
Access this book
- Available as PDF
- Read on any device
- Instant download
- Own it forever
- Compact, lightweight edition
- Dispatched in 3 to 5 business days
- Free shipping worldwide - see info
Tax calculation will be finalised at checkout
Other ways to access
Licence this eBook for your library
Institutional subscriptions
Table of contents (10 chapters)
Front matter, introduction.
William L. Hamilton
Background and Traditional Approaches
Node embeddings, neighborhood reconstruction methods, multi-relational data and knowledge graphs, graph neural networks, the graph neural network model, graph neural networks in practice, theoretical motivations, generative graph models, traditional graph generation approaches, deep generative models, back matter, about this book.
Graph-structured data is ubiquitous throughout the natural and social sciences, from telecommunication networks to quantum chemistry. Building relational inductive biases into deep learning architectures is crucial for creating systems that can learn, reason, and generalize from this kind of data. Recent years have seen a surge in research on graph representation learning, including techniques for deep graph embeddings, generalizations of convolutional neural networks to graph-structured data, and neural message-passing approaches inspired by belief propagation. These advances in graph representation learning have led to new state-of-the-art results in numerous domains, including chemical synthesis, 3D vision, recommender systems, question answering, and social network analysis.
This book provides a synthesis and overview of graph representation learning. It begins with a discussion of the goals of graph representation learning as well as key methodological foundations in graph theory and network analysis. Following this, the book introduces and reviews methods for learning node embeddings, including random-walk-based methods and applications to knowledge graphs. It then provides a technical synthesis and introduction to the highly successful graph neural network (GNN) formalism, which has become a dominant and fast-growing paradigm for deep learning with graph data. The book concludes with a synthesis of recent advancements in deep generative models for graphs—a nascent but quickly growing subset of graph representation learning.
Authors and Affiliations
Mcgill university, canada, mila-quebec artificial intelligence institute, canada, about the author, bibliographic information.
Book Title : Graph Representation Learning
Authors : William L. Hamilton
Series Title : Synthesis Lectures on Artificial Intelligence and Machine Learning
DOI : https://doi.org/10.1007/978-3-031-01588-5
Publisher : Springer Cham
eBook Packages : Synthesis Collection of Technology (R0) , eBColl Synthesis Collection 10
Copyright Information : Springer Nature Switzerland AG 2020
Softcover ISBN : 978-3-031-00460-5 Published: 16 September 2020
eBook ISBN : 978-3-031-01588-5 Published: 01 June 2022
Series ISSN : 1939-4608
Series E-ISSN : 1939-4616
Edition Number : 1
Number of Pages : XVII, 141
Topics : Artificial Intelligence , Machine Learning , Mathematical Models of Cognitive Processes and Neural Networks
- Publish with us
Policies and ethics
- Find a journal
- Track your research
Graph Representation Learning
This book is a foundational guide to graph representation learning, including state-of-the art advances, and introduces the highly successful graph neural network (GNN) formalism.
Graph-structured data is ubiquitous throughout the natural and social sciences, from telecommunication networks to quantum chemistry. Building relational inductive biases into deep learning architectures is crucial for creating systems that can learn, reason, and generalize from this kind of data. Recent years have seen a surge in research on graph representation learning, including techniques for deep graph embeddings, generalizations of convolutional neural networks to graph-structured data, and neural message-passing approaches inspired by belief propagation. These advances in graph representation learning have led to new state-of-the-art results in numerous domains, including chemical synthesis, 3D vision, recommender systems, question answering, and social network analysis.
It begins with a discussion of the goals of graph representation learning as well as key methodological foundations in graph theory and network analysis. Following this, the book introduces and reviews methods for learning node embeddings, including random-walk-based methods and applications to knowledge graphs. It then provides a technical synthesis and introduction to the highly successful graph neural network (GNN) formalism, which has become a dominant and fast-growing paradigm for deep learning with graph data. The book concludes with a synthesis of recent advancements in deep generative models for graphs -- a nascent but quickly growing subset of graph representation learning.
IEEE Account
- Change Username/Password
- Update Address
Purchase Details
- Payment Options
- Order History
- View Purchased Documents
Profile Information
- Communications Preferences
- Profession and Education
- Technical Interests
- US & Canada: +1 800 678 4333
- Worldwide: +1 732 981 0060
- Contact & Support
- About IEEE Xplore
- Accessibility
- Terms of Use
- Nondiscrimination Policy
- Privacy & Opting Out of Cookies
A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity. © Copyright 2024 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.
William L. Hamilton
Note that I am no longer accepting new students, as I have shifted away from my full-time role at McGill University to an adjunct position.
- Publications
COMP 451 --- Fundamentals of Machine Learning
In the winter semester of 2021, I will teach a course on the Fundamentals of Machine Learning at McGill. Check out the course website for more information.
COMP 551 --- Applied Machine Learning
I teach a course on Applied Machine Learning at McGill. I taught the course in the winter semester of 2019 as well as in the fall of 2019. Check out the course website for more information.
COMP 766 --- Graph Representation Learning
In winter 2020, I taught a graduate-level course on Graph Representation Learning. Check out the course website for more information.
PhD Students
Msc students.
Adjunct Professor McGill University, Mila
CV (short version) --> CV --> Google Scholar
Many thanks to David Jurgens for the site template/inspiration
The Online Books Page
Graph representation learning.
Help with reading books -- Report a bad link -- Suggest a new listing
Home -- Search -- New Listings -- Authors -- Titles -- Subjects -- Serials
Books -- News -- Features -- Archives -- The Inside Story
Edited by John Mark Ockerbloom (onlinebooks@pobox.upenn.edu) Data for this curated collection listing is CC0. See OBP copyrights and licenses .
Help | Advanced Search
Computer Science > Social and Information Networks
Title: representation learning on graphs: methods and applications.
Abstract: Machine learning on graphs is an important and ubiquitous task with applications ranging from drug design to friendship recommendation in social networks. The primary challenge in this domain is finding a way to represent, or encode, graph structure so that it can be easily exploited by machine learning models. Traditionally, machine learning approaches relied on user-defined heuristics to extract features encoding structural information about a graph (e.g., degree statistics or kernel functions). However, recent years have seen a surge in approaches that automatically learn to encode graph structure into low-dimensional embeddings, using techniques based on deep learning and nonlinear dimensionality reduction. Here we provide a conceptual review of key advancements in this area of representation learning on graphs, including matrix factorization-based methods, random-walk based algorithms, and graph neural networks. We review methods to embed individual nodes as well as approaches to embed entire (sub)graphs. In doing so, we develop a unified framework to describe these recent approaches, and we highlight a number of important applications and directions for future work.
Submission history
Access paper:.
- Other Formats
References & Citations
- Google Scholar
- Semantic Scholar
1 blog link
Dblp - cs bibliography, bibtex formatted citation.
Bibliographic and Citation Tools
Code, data and media associated with this article, recommenders and search tools.
- Institution
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .
- Find a Library
- Browse Collections
- Graph Representation Learning
ebook ∣ Synthesis Lectures on Artificial Intelligence and Machine Learning
By william l. hamilton.
Add Book To Favorites
Is this your library?
Sign up to save your library.
With an OverDrive account, you can save your favorite libraries for at-a-glance information about availability. Find out more about OverDrive accounts.
Synthesis Lectures on Artificial Intelligence and Machine Learning
William L. Hamilton
Morgan & Claypool Publishers
16 September 2020
Find this title in Libby, the library reading app by OverDrive.
IMAGES
VIDEO
COMMENTS
William L. Hamilton, McGill University. The field of graph representation learning has grown at an incredible (and sometimes unwieldy) pace over the past seven years, transforming from a small subset of researchers working on a relatively niche topic to one of the fastest growing sub-areas of deep learning. This book is my attempt to provide a ...
Graph Representation Learning William L. Hamilton McGill University 2020 Pre-publication draft of a book to be published by Morgan & Claypool publishers. Unedited version released with permission. All relevant copyrights held by the author and publisher extend to this pre-publication draft. Citation: William L. Hamilton. (2020). Graph ...
These advances in graph representation learning have led to new state-of-the-art results in numerous domains, including chemical synthesis, 3D vision, recommender systems, question answering, and social network analysis. ... William L. Hamilton is an Assistant Professor of Computer Science at McGill University and a Canada CIFAR Chair in AI ...
Graph Representation Learning. William L. Hamilton. Morgan & Claypool Publishers, Sep 16, 2020 - Computers - 159 pages. This book is a foundational guide to graph representation learning, including state-of-the art advances, and introduces the highly successful graph neural network (GNN) formalism. Graph-structured data is ubiquitous throughout ...
This book is a foundational guide to graph representation learning, including state-of-the art advances, and introduces the highly successful graph neural network (GNN) formalism. Graph-structured data is ubiquitous throughout the natural and social sciences, from telecommunication networks to quantum chemistry.
2019. TLDR. This work proposes Graphite, an algorithmic framework for unsupervised learning of representations over nodes in large graphs using deep latent variable generative models, parameterizes variational autoencoders (VAE) with graph neural networks, and uses a novel iterative graph refinement strategy inspired by low-rank approximations ...
William L. Hamilton is an Assistant Professor of Computer Science at McGill University and a Canada CIFAR Chair in AI. His research focuses on graph representation learning as well as applications in computational social science and biology.
These advances in graph representation learning have led to new state-of-the-art results in numerous domains, including chemical synthesis, 3D vision, recommender systems, question answering, and social network analysis. ... William L. Hamilton is an Assistant Professor of Computer Science at McGill University and a Canada CIFAR Chair in AI ...
William L. Hamilton. 4.53. 30 ratings4 reviews. This book is a foundational guide to graph representation learning, including state-of-the art advances, and introduces the highly successful graph neural network (GNN) formalism. Graph-structured data is ubiquitous throughout the natural and social sciences, from telecommunication networks to ...
pdf (arxiv) Graph Representation Learning. William L. Hamilton. Morgan and Claypool Publishers. 2020. pdf. Distilling Structured Knowledge for Text-Based Relational Reasoning. Jin Dong, Marc-Antoine Rondeau, and William L. Hamilton. Proceedings of EMNLP. 2020. TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion.
Machine learning. Subject: Neural networks (Computer science) Subject: Graph theory -- Data processing. Call number: Q325.5 .H364 2020. Other copies: Look for editions of this book at your library, or elsewhere.
William L. Hamilton is an Assistant Professor of Computer Science at McGill University and a Canada CIFAR Chair in AI. His research focuses on graph representation learning as well as applications in computational social science and biology. In recent years, he has published more than 20 papers on graph representation learning at top-tier venues across machine learning and network science, as ...
Representation Learning on Graphs: Methods and Applications. William L. Hamilton, Rex Ying, Jure Leskovec. Machine learning on graphs is an important and ubiquitous task with applications ranging from drug design to friendship recommendation in social networks. The primary challenge in this domain is finding a way to represent, or encode, graph ...
Representation Learning on Graphs: Methods and Applications William L. Hamilton [email protected] Rex Ying [email protected] Jure Leskovec [email protected] Department of Computer Science Stanford University Stanford, CA, 94305 Abstract Machine learning on graphs is an important and ubiquitous task with applications ranging from drug
These advances in graph representation learning have led to new state-of-the-art results in numerous domains, including chemical synthesis, 3D vision, recommender systems, question answering, and social network analysis. This book provides a synthesis and overview of graph representation learning.
This book is a foundational guide to graph representation learning, including state-of-the art advances, and introduces the highly successful graph neural network (GNN) formalism. Graph-structured data is ubiquitous throughout the natural and social sciences, from telecommunication networks to quantum chemistry.
Graph Representation Learning. William L. Hamilton. Springer Nature, Jun 1, 2022 - Computers - 141 pages. Graph-structured data is ubiquitous throughout the natural and social sciences, from telecommunication networks to quantum chemistry. Building relational inductive biases into deep learning architectures is crucial for creating systems that ...
Recent Advances and Open ChallengesGraph-structured data is ubiquitous throughout the natural and social sciences, from telecommunication networks to quantum...
This book is a foundational guide to graph representation learning, including state-of-the art advances, and introduces the highly successful graph neural network (GNN) formalism.Graph-structured data is ubiquitous throughout the natural and social sciences, from telecommunication networks to quantum chemistry. Building relational inductive biases into deep learning architectures is crucial ...
William L. Hamilton. Publisher. Morgan & Claypool Publishers. Release. 16 September 2020. Share. Subjects ... This book is a foundational guide to graph representation learning, including state-of-the art advances, and introduces the highly successful graph neural network (GNN) formalism. ...
Instructor: William L. Hamilton; Term: Winter 2020; When: Mondays and Wednesdays, 1:05-2:25pm; Where: MC 12 Note the room change! Description. Graph representation learning (GRL) is a quickly growing subfield of machine learning that seeks to apply machine learning methods to graph-structured data. Machine learning on graphs is an important and ...
Recent years have seen a surge in research on graph representation learning, including techniques for deep graph embeddings, generalizations of convolutional neural networks to graph-structured data, and neural message-passing approaches inspired by belief propagation.
William L. Hamilton. Morgan & Claypool Publishers, 2020 - Computers - 159 pages. This book is a foundational guide to graph representation learning, including state-of-the art advances, and introduces the highly successful graph neural network (GNN) formalism. Graph-structured data is ubiquitous throughout the natural and social sciences, from ...