graph2vec: Learning Distributed Representations of Graphs

17 Jul 2017Annamalai NarayananMahinthan ChandramohanRajasekar VenkatesanLihui ChenYang LiuShantanu Jaiswal

Recent works on representation learning for graph structured data predominantly focus on learning distributed representations of graph substructures such as nodes and subgraphs. However, many graph analytics tasks such as graph classification and clustering require representing entire graphs as fixed length feature vectors... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Graph Classification MUTAG Graph2Vec Accuracy 83.15% # 30
Graph Classification NCI1 Graph2Vec Accuracy 73.22% # 20
Graph Classification NCI109 Graph2Vec Accuracy 74.26 # 10
Graph Classification PROTEINS Graph2Vec Accuracy 60.17% # 45