When Work Matters: Transforming Classical Network Structures to Graph CNN

7 Jul 2018Wenting ZhaoChunyan XuZhen CuiTong ZhangJiatao JiangZhenyu ZhangJian 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.).. (read more)

PDF Abstract

Code


No code implementations yet. Submit your code now

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Graph Classification COLLAB G_DenseNet Accuracy 83.16% # 2
Graph Classification ENZYMES G_Inception Accuracy 67.50% # 4
Graph Classification IMDb-B G_ResNet Accuracy 79.90% # 1
Graph Classification IMDb-M G_ResNet Accuracy 54.53% # 2
Graph Classification MUTAG G_Inception Accuracy 95.00% # 1
Graph Classification NCI109 G_DenseNet Accuracy 80.66 # 7
Graph Classification PTC G_DenseNet Accuracy 73.24 # 5