이종 그래프상의 비유클리디안 데이터 분석을 위한 쌍곡 그래프 변형 인공 신경망

다국어 초록 (Multilingual Abstract)

Convolution Neural Networks (CNNs), which are based on convolution operations, are used for various tasks in image classification, image generation, time series analysis, etc. Since the convolution operations are not directly applicable to non-Euclidean spaces such as graphs and manifolds, a variety of Graph Neural Networks (GNNs) have extended convolutional neural networks to homogeneous graphs, which has a single type of edges and nodes. However, in real-world applications, heterogeneous and hierarchical graph data often occur. To expand the operating range of GNNs to the graphs that have multiple types of nodes and edges with the hierarchy, herein, we propose a new model that integrates Hyperbolic Graph Convolution Networks (HGCNs) and Graph Transformer Networks (GTNs).

참고문헌 (Reference)

1 T. N. Kipf, "Variational graph auto-encoders" 2016

2 F. Scarselli, "The graph neural network model" 20 (20): 61-80, 2018

3 D. Wang, "Structural deep network embedding" 1225-1234, 2016

4 J. Bruna, "Spectral networks and locally connected networks on graphs"

5 S. Bhagat, "Social Network Data Analytics" 115-148, 2011

6 T. N. Kipf, "Semi-supervised classification with graph convolutional networks" 2017

7 M. Schlichtkrull, "Modeling relational data with graph convolutional networks" 593-607, 2018

8 M. Zhang, "Link prediction based on graph neural networks" 5165-5175, 2018

9 W. Hamilton, "Inductive representation learning on large graphs" 1024-1034, 2017

10 I. Chami, "Hyperbolic graph convolutional neural networks" 4868-4879, 2019

11 X. Wang, "Heterogeneous graph attention network" 2022-2032, 2019

12 B. Xu, "Graph wavelet neural network" 2019

13 S. Yun, "Graph transformer networks" 2019

14 R. Ying, "Graph convolutional neural networks for web-scale recommender systems" 974-983, 2018

15 R. van den Berg, "Graph convolutional matrix completion"

16 P. Veličković, "Graph attention networks" 2018

17 F. Monti, "Geometric matrix completion with recurrent multigraph neural networks" 3697-3707, 2017

18 J. Chen, "FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling" 2018

19 T. Lei, "Deriving neural architectures from sequence and graph kernels" 70 : 2024-2033, 2017

20 M. Henaff, "Deep convolutional networks on graph-structured data"

21 M. Defferrard, "Convolutional neural networks on graphs with fast localized spectral filtering" 3844-3852, 2016

22 P. Y. Simard, "Best practices for convolutional neural networks applied to visual document analysis" 3 (3): 2003

23 D. Kingma, "Adam: A method for stochastic optimization" 2018