When Work Matters: Transforming Classical Network Structures to Graph CNN

7 Jul 2018  ·  Wenting Zhao, Chunyan Xu, Zhen Cui, Tong Zhang, Jiatao Jiang, Zhen-Yu Zhang, Jian Yang ·

Numerous pattern recognition applications can be formed as learning from graph-structured data, including social network, protein-interaction network, the world wide web data, knowledge graph, etc. While convolutional neural network (CNN) facilitates great advances in gridded image/video understanding tasks, very limited attention has been devoted to transform these successful network structures (including Inception net, Residual net, Dense net, etc.) to establish convolutional networks on graph, due to its irregularity and complexity geometric topologies (unordered vertices, unfixed number of adjacent edges/vertices). In this paper, we aim to give a comprehensive analysis of when work matters by transforming different classical network structures to graph CNN, particularly in the basic graph recognition problem. Specifically, we firstly review the general graph CNN methods, especially in its spectral filtering operation on the irregular graph data. We then introduce the basic structures of ResNet, Inception and DenseNet into graph CNN and construct these network structures on graph, named as G_ResNet, G_Inception, G_DenseNet. In particular, it seeks to help graph CNNs by shedding light on how these classical network structures work and providing guidelines for choosing appropriate graph network frameworks. Finally, we comprehensively evaluate the performance of these different network structures on several public graph datasets (including social networks and bioinformatic datasets), and demonstrate how different network structures work on graph CNN in the graph recognition task.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Graph Classification COLLAB G_DenseNet Accuracy 83.16% # 4
Graph Classification ENZYMES G_Inception Accuracy 67.50% # 10
Graph Classification IMDb-B G_ResNet Accuracy 79.90% # 3
Graph Classification IMDb-M G_ResNet Accuracy 54.53% # 6
Graph Classification MUTAG G_Inception Accuracy 95.00% # 5
Graph Classification NCI109 G_DenseNet Accuracy 80.66 # 14
Graph Classification PTC G_DenseNet Accuracy 73.24% # 7

Methods