建國科技大學圖書館 |

語系: 繁體中文

說明(常見問題)

圖書館個人資料蒐集告知聲明

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Graph representation learning

Hamilton, William L.

Graph representation learning

紀錄類型:	書目-語言資料,印刷品 : 單行本
作者:	HamiltonWilliam L.,
出版地:	[San Rafael, California]
出版者:	Morgan & Claypool Publishers;
出版年:	c2020.
面頁冊數:	xvii, 141 p.ill. : 24 cm.;
集叢名:	Synthesis lectures on artificial intelligence and machine learninglecture #46
標題:	Machine learning. -
標題:	Neural networks (Computer science) -
標題:	Graph theory - Data processing. -
摘要註:	"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."--Back cover.
ISBN:	9781681739632

Graph representation learning
Hamilton, William L.

Graph representation learning / William L. Hamilton. - [San Rafael, California] : Morgan & Claypool Publishers, c2020.. - xvii, 141 p. ; ill. ; 24 cm.. - (Synthesis lectures on artificial intelligence and machine learning ; lecture #46).
Includes bibliographical references (p. 131-140).
ISBN 9781681739632ISBN 1681739631
Machine learning.Neural networks (Computer science)Graph theory -- Data processing.

Graph representation learning
LDR:02472cam a2200241 450 001 393713
010 1 $a 9781681739632 $b pbk. $d NT1668
010 1 $a 1681739631 $b pbk.
010 1 $z 9781681739656 $b ebk.
100 $a 20210910d2020 k y0engy50 b
101 0 $a eng
102 $a us
105 $a a a 000yy
200 1 $a Graph representation learning $f William L. Hamilton.
210 $a [San Rafael, California] $c Morgan & Claypool Publishers $d c2020.
215 1 $a xvii, 141 p. $c ill. $d 24 cm.
225 2 $a Synthesis lectures on artificial intelligence and machine learning $v lecture #46
320 $a Includes bibliographical references (p. 131-140)
330 $a "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."--Back cover.
410 0 $1 2001 $a Synthesis lectures on artificial intelligence and machine learning $v 46.
410 0 $1 2001 $a Synthesis lectures on artificial intelligence and machine learning $v lecture #46
606 $a Machine learning. $2 lc $3 32680
606 $a Neural networks (Computer science) $2 lc $3 39781
606 $a Graph theory $x Data processing. $2 lc $3 110875
676 $a 006.3/1 $v 23
680 $a Q325.5 $b .H364 2020
700 1 $a Hamilton $b William L. $3 385921
801 0 $a cw $b CTU $c 20210910 $g AACR2