Khandelwal / Das Applied Deep Learning on Graphs

Leverage graph data for business applications using specialized deep learning architectures
1. Auflage 2025
ISBN: 978-1-83588-597-0
Verlag: De Gruyter
Format: EPUB
Kopierschutz: 0 - No protection

E-Book, Englisch, 250 Seiten

With their combined expertise spanning cutting-edge AI product development at industry giants such as Walmart, Adobe, Samsung, and Arista Networks, Lakshya and Subhajoy provide real-world insights into the transformative world of graph neural networks (GNNs).
This book demystifies GNNs, guiding you from foundational concepts to advanced techniques and real-world applications. You'll see how graph data structures power today's interconnected world, why specialized deep learning approaches are essential, and how to address challenges with existing methods. You'll start by dissecting early graph representation techniques such as DeepWalk and node2vec. From there, the book takes you through popular GNN architectures, covering graph convolutional and attention networks, autoencoder models, LLMs, and technologies such as retrieval augmented generation on graph data. With a strong theoretical grounding, you'll seamlessly navigate practical implementations, mastering the critical topics of scalability, interpretability, and application domains such as NLP, recommendations, and computer vision.
By the end of this book, you'll have mastered the underlying ideas and practical coding skills needed to innovate beyond current methods and gained strategic insights into the future of GNN technologies.

Autoren/Hrsg.

Khandelwal, Lakshya

Das, Subhajoy

Fachgebiete

• Mathematik | Informatik EDV | Informatik EDV & Informatik Allgemein

Über Autor(innen)

Khandelwal Lakshya :

Lakshya Khandelwal holds a bachelor's and master's degree from IIT Kanpur in mathematics and computer science and has 8+ years of experience in building scalable machine learning products for multiple tech giants. He has worked as a lead ML engineer with Samsung, building natural language intelligence for the very first version of Bixby. He has also worked as a data scientist with Adobe, developing search bid optimization solutions as part of the advertising cloud suite for major enterprises across the globe. In addition, he has led natural language and forecasting initiatives at Walmart, building next-generation AI products for millions of customers. Lakshya currently leads AI for AirMDR, building agentic AI for the cybersecurity domain.Das Subhajoy :

Subhajoy Das is a staff data scientist with 7 years of experience under his belt. He graduated from IIT Kharagpur with a bachelor's and master's degree in mathematics and computing. Since then, he has worked in organizations at varying stages of growth: from fast-growing e-commerce start-ups such as Meesho to behemoths such as Adobe. He has driven several pivotal features in every company he has worked in, including building an end-to-end recommendation system for the Meesho app and curating interesting advertising using reinforcement learning-based optimizations in Adobe Advertising. He is currently working at Arista Networks, building AI-driven apps that are responsible for the cybersecurity of several Fortune 500 companies.