000 04326nam a22005415i 4500
001 978-3-031-01587-8
003 DE-He213
005 20240730163429.0
007 cr nn 008mamaa
008 220601s2020 sz | s |||| 0|eng d
020 _a9783031015878
_9978-3-031-01587-8
024 7 _a10.1007/978-3-031-01587-8
_2doi
050 4 _aQ334-342
050 4 _aTA347.A78
072 7 _aUYQ
_2bicssc
072 7 _aCOM004000
_2bisacsh
072 7 _aUYQ
_2thema
082 0 4 _a006.3
_223
100 1 _aLiu, Zhiyuan.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
_978468
245 1 0 _aIntroduction to Graph Neural Networks
_h[electronic resource] /
_cby Zhiyuan Liu, Jie Zhou.
250 _a1st ed. 2020.
264 1 _aCham :
_bSpringer International Publishing :
_bImprint: Springer,
_c2020.
300 _aXVII, 109 p.
_bonline resource.
336 _atext
_btxt
_2rdacontent
337 _acomputer
_bc
_2rdamedia
338 _aonline resource
_bcr
_2rdacarrier
347 _atext file
_bPDF
_2rda
490 1 _aSynthesis Lectures on Artificial Intelligence and Machine Learning,
_x1939-4616
505 0 _aPreface -- Acknowledgments -- Introduction -- Basics of Math and Graph -- Basics of Neural Networks -- Vanilla Graph Neural Networks -- Graph Convolutional Networks -- Graph Recurrent Networks -- Graph Attention Networks -- Graph Residual Networks -- Variants for Different Graph Types -- Variants for Advanced Training Methods -- General Frameworks -- Applications -- Structural Scenarios -- Applications -- Non-Structural Scenarios -- Applications -- Other Scenarios -- Open Resources -- Conclusion -- Bibliography -- Authors' Biographies.
520 _aGraphs 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.
650 0 _aArtificial intelligence.
_93407
650 0 _aMachine learning.
_91831
650 0 _aNeural networks (Computer science) .
_978469
650 1 4 _aArtificial Intelligence.
_93407
650 2 4 _aMachine Learning.
_91831
650 2 4 _aMathematical Models of Cognitive Processes and Neural Networks.
_932913
700 1 _aZhou, Jie.
_eauthor.
_4aut
_4http://id.loc.gov/vocabulary/relators/aut
_978470
710 2 _aSpringerLink (Online service)
_978471
773 0 _tSpringer Nature eBook
776 0 8 _iPrinted edition:
_z9783031000324
776 0 8 _iPrinted edition:
_z9783031004599
776 0 8 _iPrinted edition:
_z9783031027154
830 0 _aSynthesis Lectures on Artificial Intelligence and Machine Learning,
_x1939-4616
_978472
856 4 0 _uhttps://doi.org/10.1007/978-3-031-01587-8
912 _aZDB-2-SXSC
942 _cEBK
999 _c84596
_d84596