"Graph Neural Networks in Action" is a comprehensive guide designed for enthusiasts, data scientists, and machine learning practitioners eager to delve into the innovative world of Graph Neural Networks (GNNs). This meticulously crafted book walks you through the foundational concepts, advanced techniques, and practical applications of GNNs in a structured and engaging manner.
NOTE (11/26/2023): There is a very recent issue with the OGB datasets that is preventing a download of the Amazon Products dataset. We will continue to check on the status of the problem and update this space. (snap-stanford/ogb#463)
Embark on your journey with an insightful exploration of GNNs, where you'll unravel their underlying principles and potential applications.
-
Chapter 1: Discovering GNNs
Unravel the mystique of GNNs, their origins, evolution, and the pivotal role they play in drawing actionable insights from intricate graph data. -
Chapter 2: Graph Data Models and Data Pipelining
Dive deep into the core of graph data structures, data modeling techniques, and efficient pipelining strategies essential for handling complex graph data. -
Chapter 3: Graph Embeddings
Master the art and science of translating graph data into vector spaces, opening doors to a universe of machine learning applications.
Venture into the core architectures and algorithms that power GNNs, illustrated with real-world applications and hands-on examples.
-
Chapter 4: Graph Convolutional Networks and GraphSAGE
A detailed exploration of GCNs and GraphSAGE, unveiling their architectural nuances, operational principles, and implementation details. -
Chapter 5: Graph Attention Networks
Discover the elegance of GANs in capturing the intricate dependencies in graph data, backed with practical examples and case studies. -
Chapter 6: Graph AutoEncoders
Unearth the potential of autoencoders in generating powerful graph embeddings, with a touch of hands-on implementations.
Take a giant leap into the advanced realms of GNNs, uncovering cutting-edge techniques and large-scale applications.
-
Chapter 7: Dynamic Graphs: Spatial-Temporal GNNs
Step into the dynamic world where graphs evolve over time, and learn the specialized GNNs that capture spatial-temporal patterns. -
Chapter 8: Learning at Scale
Master the strategies and techniques to scale GNNs for handling massive, real-world graph data, ensuring efficiency and performance.
Equip yourself with the foundational concepts of graph theory and get up and running with the frameworks utilized throughout the book.
-
Appendix A: Discovering Graphs
A refresher to the fascinating world of graphs, preparing you for the intricate journey ahead. -
Appendix B: Installing and Configuring the Frameworks in This Book
A practical guide to seamlessly set up and configure the frameworks, ensuring a hassle-free learning experience.
This repository contains the source code, datasets, and supplemental resources corresponding to each chapter of "Graph Neural Networks in Action". Navigate through the organized folders, each encapsulating the codes, examples, and datasets integral to the respective chapters, aiding in a hands-on and interactive learning experience.
Clone this repository, dive into the rich source code, and embark on an enlightening journey to master Graph Neural Networks. Happy Learning!
Feel free to contribute, raise issues, or propose enhancements to make this repository a comprehensive resource for everyone venturing into GNNs.