.

Скачать книгу

Acknowledgments

       1 Introduction

       1.1 Motivations

       1.1.1 Convolutional Neural Networks

       1.1.2 Network Embedding

       1.2 Related Work

       2 Basics of Math and Graph

       2.1 Linear Algebra

       2.1.1 Basic Concepts

       2.1.2 Eigendecomposition

       2.1.3 Singular Value Decomposition

       2.2 Probability Theory

       2.2.1 Basic Concepts and Formulas

       2.2.2 Probability Distributions

       2.3 Graph Theory

       2.3.1 Basic Concepts

       2.3.2 Algebra Representations of Graphs

       3 Basics of Neural Networks

       3.1 Neuron

       3.2 Back Propagation

       3.3 Neural Networks

       4 Vanilla Graph Neural Networks

       4.1 Introduction

       4.2 Model

       4.3 Limitations

       5 Graph Convolutional Networks

       5.1 Spectral Methods

       5.1.1 Spectral Network

       5.1.2 ChebNet

       5.1.3 GCN

       5.1.4 AGCN

       5.2 Spatial Methods

       5.2.1 Neural FPs

       5.2.2 PATCHY-SAN

       5.2.3 DCNN

       5.2.4 DGCN

       5.2.5 LGCN

       5.2.6 MoNet

       5.2.7 GraphSAGE

       6 Graph Recurrent Networks

       6.1 Gated Graph Neural Networks

       6.2 Tree LSTM

       6.3 Graph LSTM

       6.4 Sentence LSTM

       7 Graph Attention Networks

       7.1 GAT

       7.2 GAAN

       8 Graph Residual Networks

       8.1 Highway GCN

       8.2 Jump Knowledge Network

       8.3 DeepGCNs

       9 Variants for Different Graph Types

       9.1 Directed Graphs

       9.2 Heterogeneous Graphs

      

Скачать книгу