Introduction to Graph Neural Networks, Liu Zhiyuan, Zhou Jie

Автор: Xingni Zhou, Zhiyuan Ren, Yanzhuo Ma, Kai Fan, Ji Xiang
Название: Data structures based on linear relations
ISBN: 3110595575 ISBN-13(EAN): 9783110595574
Издательство: Walter de Gruyter
Цена: 12078.00 р.
Наличие на складе: Есть у поставщика Поставка под заказ.

Описание:

Data structures is a key course for computer science and related majors. This book presents a variety of practical or engineering cases and derives abstract concepts from concrete problems. Besides basic concepts and analysis methods, it introduces basic data types such as sequential list, tree as well as graph. This book can be used as an undergraduate textbook, as a training textbook or a self-study textbook for engineers.

Автор: Xingni Zhou, Zhiyuan Ren, Yanzhuo Ma, Kai Fan, Ji Xiang
Название: Non-linear Data Structures and Data Processing
ISBN: 3110676052 ISBN-13(EAN): 9783110676051
Издательство: Walter de Gruyter
Цена: 12078.00 р.
Наличие на складе: Есть у поставщика Поставка под заказ.

Описание:

The systematic description starts with basic theory and applications of different kinds of data structures, including storage structures and models. It also explores on data processing methods such as sorting, index and search technologies. Due to its numerous exercises the book is a helpful reference for graduate students, lecturers.

Автор: Liu Zhiyuan, Zhou Jie
Название: Introduction to Graph Neural Networks
ISBN: 1681737655 ISBN-13(EAN): 9781681737652
Издательство: Mare Nostrum (Eurospan)
Рейтинг:
Цена: 6376.00 р.
Наличие на складе: Нет в наличии.

Описание: Graphs are useful data structures in complex real-life applications such as modeling physical systems, learning molecular fingerprints, controlling traffic networks, and recommending friends in social networks.

However, these tasks require dealing with non-Euclidean graph data that contains rich relational information between elements and cannot be well handled by traditional deep learning models (e.g., convolutional neural networks (CNNs) or recurrent neural networks (RNNs)). Nodes in graphs usually contain useful feature information that cannot be well addressed in most unsupervised representation learning methods (e.g., network embedding methods). Graph neural networks (GNNs) are proposed to combine the feature information and the graph structure to learn better representations on graphs via feature propagation and aggregation. Due to its convincing performance and high interpretability, GNN has recently become a widely applied graph analysis tool.

This book provides a comprehensive introduction to the basic concepts, models, and applications of graph neural networks. It starts with the introduction of the vanilla GNN model. Then several variants of the vanilla model are introduced such as graph convolutional networks, graph recurrent networks, graph attention networks, graph residual networks, and several general frameworks. Variants for different graph types and advanced training methods are also included. As for the applications of GNNs, the book categorizes them into structural, non-structural, and other scenarios, and then it introduces several typical models on solving these tasks. Finally, the closing chapters provide GNN open resources and the outlook of several future directions.