Muutke küpsiste eelistusi

Machine Learning in Social Networks: Embedding Nodes, Edges, Communities, and Graphs 1st ed. 2021 [Pehme köide]

,
  • Formaat: Paperback / softback, 112 pages, kõrgus x laius: 235x155 mm, kaal: 454 g, 18 Illustrations, color; 11 Illustrations, black and white; XI, 112 p. 29 illus., 18 illus. in color., 1 Paperback / softback
  • Sari: SpringerBriefs in Computational Intelligence
  • Ilmumisaeg: 26-Nov-2020
  • Kirjastus: Springer Verlag, Singapore
  • ISBN-10: 9813340215
  • ISBN-13: 9789813340213
Teised raamatud teemal:
  • Pehme köide
  • Hind: 62,59 €*
  • * hind on lõplik, st. muud allahindlused enam ei rakendu
  • Tavahind: 73,64 €
  • Säästad 15%
  • Raamatu kohalejõudmiseks kirjastusest kulub orienteeruvalt 2-4 nädalat
  • Kogus:
  • Lisa ostukorvi
  • Tasuta tarne
  • Tellimisaeg 2-4 nädalat
  • Lisa soovinimekirja
Machine Learning in Social Networks: Embedding Nodes, Edges, Communities, and Graphs 1st ed. 2021Suurem pilt
  • Formaat: Paperback / softback, 112 pages, kõrgus x laius: 235x155 mm, kaal: 454 g, 18 Illustrations, color; 11 Illustrations, black and white; XI, 112 p. 29 illus., 18 illus. in color., 1 Paperback / softback
  • Sari: SpringerBriefs in Computational Intelligence
  • Ilmumisaeg: 26-Nov-2020
  • Kirjastus: Springer Verlag, Singapore
  • ISBN-10: 9813340215
  • ISBN-13: 9789813340213
Teised raamatud teemal:
Püsilink: https://www.kriso.ee/db/9789813340213.html

This book deals with network representation learning. It deals with embedding nodes, edges, subgraphs and graphs. There is a growing interest in understanding complex systems in different domains including health, education, agriculture and transportation. Such complex systems are analyzed by modeling, using networks that are aptly called complex networks. Networks are becoming ubiquitous as they can represent many real-world relational data, for instance, information networks, molecular structures, telecommunication networks and protein–protein interaction networks. Analysis of these networks provides advantages in many fields such as recommendation (recommending friends in a social network), biological field (deducing connections between proteins for treating new diseases) and community detection (grouping users of a social network according to their interests) by leveraging the latent information of networks. An active and important area of current interest is to come out with algorithms that learn features by embedding nodes or (sub)graphs into a vector space. These tasks come under the broad umbrella of representation learning. A representation learning model learns a mapping function that transforms the graphs' structure information to a low-/high-dimension vector space maintaining all the relevant properties. 

1 Introduction
1(6)
1.1 Introduction
1(4)
1.2 Notation
5(1)
1.3 Contents Covered in This Book
5(2)
2 Representations of Networks
7(28)
2.1 Introduction
7(1)
2.2 Networks Represented as Graphs
8(1)
2.3 Data Structures to Represent Graphs
9(2)
2.3.1 Matrix Representation
9(1)
2.3.2 Adjacency List
10(1)
2.4 Network Embeddings
11(2)
2.5 Experimental Datasets and Metrics
13(5)
2.5.1 Evaluation Datasets
13(1)
2.5.2 Evaluation Metrics
14(4)
2.6 Machine Learning Downstream Tasks
18(3)
2.6.1 Classification
18(1)
2.6.2 Clustering
19(1)
2.6.3 Link Prediction (LP)
20(1)
2.6.4 Visualization
20(1)
2.6.5 Network Reconstruction
21(1)
2.7 Embeddings Based on Matrix Factorization
21(6)
2.7.1 Singular Value Decomposition (SVD)
22(1)
2.7.2 Matrix Factorization Based Clustering
23(2)
2.7.3 Soft Clustering as Matrix Factorization
25(1)
2.7.4 Non-Negative Matrix Factorization (NMF)
26(1)
2.8 Word2Vec
27(3)
2.8.1 Skip-Gram Model
28(2)
2.9 Learning Network Embeddings
30(2)
2.10 Summary
32(3)
Bibliography
32(3)
3 Deep Learning
35(32)
3.1 Introduction
35(1)
3.2 Neural Networks
36(10)
3.2.1 Perceptron
36(3)
3.2.2 Characteristics of Neural Networks
39(1)
3.2.3 Multilayer Perceptron Networks
39(2)
3.2.4 Training MLP Networks
41(5)
3.3 Convolutional Neural Networks
46(8)
3.3.1 Activation Function
46(2)
3.3.2 Initialization of Weights
48(1)
3.3.3 Deep Feedforward Neural Network
49(5)
3.4 Recurrent Networks
54(8)
3.4.1 Recurrent Neural Networks
54(5)
3.4.2 Long Short Term Memory
59(3)
3.5 Learning Representations Using Autoencoders
62(3)
3.5.1 Types of Autoencoders
63(2)
3.6 Summary
65(2)
Bibliography
65(2)
4 Node Representations
67(22)
4.1 Introduction
67(1)
4.2 Random Walk Based Approaches
68(4)
4.2.1 Deep Walk: Online Learning of Social Representations
68(2)
4.2.2 Scalable Feature Learning for Networks: Node2vec
70(2)
4.3 Matrix Factorization Based Algorithms
72(3)
4.3.1 Network Representation Learning with Rich Text Information
72(1)
4.3.2 GraRep: Learning Graph Representations with Global Structural Information
73(2)
4.4 Graph Neural Networks
75(8)
4.4.1 Semi-Supervised Classification with Graph Convolutional Networks
75(2)
4.4.2 Graph Attention Network
77(1)
4.4.3 Inductive Representation Learning on Large Graphs (GraphSAGE)
78(1)
4.4.4 Jumping Knowledge Networks for Node Representations
79(2)
4.4.5 Deep Graph Infomax
81(2)
4.5 Experimental Evaluation
83(6)
4.5.1 Node Classification
83(1)
4.5.2 Node Clustering
84(1)
4.5.3 Visualization
85(2)
4.5.4 Performance Analysis
87(1)
Bibliography
87(2)
5 Embedding Graphs
89(16)
5.1 SortPool
90(2)
5.2 DIFFPOOL
92(2)
5.3 SAGPool
94(2)
5.4 GIN
96(2)
5.5 Graph U-Nets
98(2)
5.6 Experimental Evaluation
100(5)
5.6.1 Graph Classification
100(1)
5.6.2 Visualization
101(2)
Bibliography
103(2)
6 Conclusions
105(2)
Glossary 107(2)
Index 109
M.N. Murty is currently a Professor in the Department of Computer Science and Automation at the Indian Institute of Science, Bangalore. His research interests are in the area of pattern recognition, data mining, and social network analysis. 





Ms. Manasvi Aggarwal is currently pursuing her M.S. at the Indian Institute of Science, Bangalore. Her research interest is in the areas of social networks and machine learning