Graph Classification using Structural Attention

KDD 2018 John Boaz LeeRyan RossiXiangnan Kong

Graph classification is a problem with practical applications in many different domains. To solve this problem, one usually calculates certain graph statistics (i.e., graph features) that help discriminate between graphs of different classes... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Graph Classification HIV dataset GAM Accuracy 74.79% # 1
Graph Classification NCI1 GAM Accuracy 67.71% # 26
Graph Classification NCI-123 GAM Accuracy 64.79% # 1
Graph Classification NCI33 GAM Accuracy 69.58% # 1
Graph Classification NCI-83 GAM Accuracy 70.42% # 1