Subgraph Networks with Application to Structural Feature Space Expansion

21 Mar 2019Qi XuanJinhuan WangMinghao ZhaoJunkun YuanChenbo FuZhongyuan RuanGuanrong Chen

Real-world networks exhibit prominent hierarchical and modular structures, with various subgraphs as building blocks. Most existing studies simply consider distinct subgraphs as motifs and use only their numbers to characterize the underlying network... (read more)

PDF Abstract

Code


No code implementations yet. Submit your code now

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Graph Classification IMDb-B Deep WL SGN(0,1,2) Accuracy 75.70% # 7
Graph Classification MUTAG Deep WL SGN(0,1,2) Accuracy 93.68% # 4
Graph Classification NCI1 Deep WL SGN(0,1,2) Accuracy 70.26% # 36
Graph Classification NCI109 Deep WL SGN(0,1,2) Accuracy 71.06 # 15
Graph Classification PROTEINS Deep WL SGN(0,1,2) Accuracy 76.78% # 19
Graph Classification PTC Deep WL SGN(0,1,2) Accuracy 65.88% # 14

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet