Hamilton, William L. William L.
Graph Representation Learning
- ISBN 13:
- 9783031004605
- author:
- Hamilton, William L. William L.
- format:
- Paperback
- publisher:
- Springer
- language:
- English
- Publication Year:
- 2020
- Pages:
- 160
- Dimensions:
- 23.5 x 19.1 x 0.9 centimetres (0
- Genre:
- Science, Mathematics, Applied,
- Condition:
- New
- Availability:
- Item usually sent within 5 working days
Description
Graph Representation Learning provides a comprehensive overview of this rapidly evolving field. Building relational inductive biases into deep learning architectures is crucial for systems that can learn from graph-structured data, found in various domains such as telecommunication networks and quantum chemistry. The book synthesises recent advances in graph representation learning, including techniques for deep graph embeddings, neural message-passing approaches inspired by belief propagation, and methods for learning node embeddings. It also introduces the highly successful graph neural network (GNN) formalism, which has become a dominant paradigm for deep learning with graph data. Recent breakthroughs in this field have led to state-of-the-art results in areas such as chemical synthesis, 3D vision, recommender systems, question answering, and social network analysis. This book offers a valuable resource for researchers and practitioners seeking to understand the latest developments in graph representation learning.
Related Products
Related Products
Deep Learning on Graphs
Ma, Yao
Graph Machine Learning: Take graph data to the next level by applying machine learning techniques and algorithms
Stamile, Claudio
Hands-On Graph Neural Networks Using Python: Practical techniques and architectures for building powerful graph and deep learning apps with PyTorch
Labonne, Maxime
Graphs Answers: Complete Answers, Everyday Graphs/Coordinate Graphs
Robson, Peter
The Concept of Representation
Pitkin