國立虎尾科技大學 |

Introduction to graph neural networks /

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Introduction to graph neural networks // Zhiyuan Liu, Jie Zhou.
作者:	Liu, Zhiyuan,
其他作者:	Zhou, Jie,
面頁冊數:	1 online resource (129 p.)
標題:	Graph theory. -
電子資源:	https://portal.igpublish.com/iglibrary/search/MCPB0006532.html
ISBN:	9781681737652

Introduction to graph neural networks /
Liu, Zhiyuan,

Introduction to graph neural networks /Zhiyuan Liu, Jie Zhou. - 1 online resource (129 p.) - Synthesis lectures on artificial intelligence and machine learning ;45. - Synthesis lectures on artificial intelligence and machine learning ;29.

Includes bibliographical references (pages 93-108).

Access restricted to authorized users and institutions.

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.

Mode of access: World Wide Web.

ISBN: 9781681737652Subjects--Topical Terms:

527884
Graph theory.
Index Terms--Genre/Form:

554714
Electronic books.

LC Class. No.: QA76.87

Dewey Class. No.: 006

Introduction to graph neural networks /
LDR:02798nam a2200301 i 4500 001 1041756
006 m eo d
007 cr cn |||m|||a
008 211215t20202020cau ob 000 0 eng d
020 $a 9781681737652
020 $a 9781681737669
020 $a 9781681737676
035 $a MCPB0006532
040 $a iG Publishing $b eng $c iG Publishing $e rda
050 0 0 $a QA76.87
082 0 0 $a 006
100 1 $a Liu, Zhiyuan, $e author. $3 1341705
245 1 0 $a Introduction to graph neural networks / $c Zhiyuan Liu, Jie Zhou.
264 1 $a San Rafael, California : $b Morgan & Claypool Publishers, $c 2020.
264 4 $c ©2020
300 $a 1 online resource (129 p.)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
490 1 $a Synthesis lectures on artificial intelligence and machine learning ; $v 45
504 $a Includes bibliographical references (pages 93-108).
506 $a Access restricted to authorized users and institutions.
520 3 $a 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.
538 $a Mode of access: World Wide Web.
650 0 $a Graph theory. $3 527884
650 0 $a Neural networks (Computer science) $3 528588
655 4 $a Electronic books. $2 local $3 554714
700 1 $a Zhou, Jie, $e author. $3 1341706
830 0 $a Synthesis lectures on artificial intelligence and machine learning ; $v 29 $3 1136768
856 4 0 $u https://portal.igpublish.com/iglibrary/search/MCPB0006532.html