Graph Capsule Convolutional Neural Networks

By Saurabh Verma, Zhi-Li Zhang. 2018

139 citations recorded by the source corpus.

Graph Convolutional Neural Networks (GCNNs) are the most recent exciting advancement in deep learning field and their applications are quickly spreading in multi-cross-domains including bioinformatics, chemoinformatics, social networks, natural language processing and computer vision. In this paper, we expose and tackle some of the basic weaknesses of a GCNN model with a capsule idea presented in \cite{hinton2011transforming} and propose our Graph Capsule Network (GCAPS-CNN) model. In addition, we design our GCAPS-CNN model to solve especially graph classification problem which current GCNN models find challenging. Through extensive experiments, we show that our proposed Graph Capsule Network can significantly outperforms both the existing state-of-art deep learning methods and graph kernels on graph classification benchmark datasets.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jure Leskovec
2. William L. Hamilton
3. Philip S. Yu
4. Shirui Pan
5. Rex Ying
6. Jiaxuan You
7. Christopher Morris
8. Weihua Hu

In Computer Vision and Pattern Recognition

1. Shirui Pan
2. William L. Hamilton
3. Philip S. Yu
4. Chengqi Zhang
5. Jure Leskovec
6. Xiang Ren
7. Christopher Morris
8. Jiaxuan You

In Statistical and Nonlinear Physics

1. William L. Hamilton
2. Jure Leskovec
3. Philip S. Yu
4. Christopher Morris
5. Rex Ying
6. Shirui Pan
7. Jiaxuan You
8. Weihua Hu

Citations in the corpus

• How Powerful are Graph Neural Networks? (2018, methodology): “…et al., 2016; Defferrard et al., 2016; Duvenaud et al., 2015; Hamilton et al., 2017a; Kearnes et al., 2016; Kipf & Welling, 2017; Li et al., 2016; Velickovic et al., 2018; Santoro et al., 2017; Xu et al., 2018; Santoro et al., 2018; Verma & Zhang, 2018; Ying et al., 2018; Zhang et al., 2018).”
• Hierarchical Graph Representation Learning with Differentiable Pooling (2018, background): “high-order moments [37] to distinguish nodes that are similar in structure and feature space.”
• A Comprehensive Survey on Graph Neural Networks (2019, background): “Verma and Zhang propose graph capsule networks [89] which further explore the permutation invariant for graph data.”
• Capsule Graph Neural Network (2018, methodology): “2) GCAPS-CNN proposed by Verma & Zhang (2018) also introduced capsule-related concept into graph representation learning.”