MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding

5 Feb 2020Xinyu FuJiani ZhangZiqiao MengIrwin King

A large number of real-world graphs or networks are inherently heterogeneous, involving a diversity of node types and relation types. Heterogeneous graph embedding is to embed rich structural and semantic information of a heterogeneous graph into low-dimensional node representations... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Node Clustering DBLP MAGNN NMI 80.81 # 1
ARI 85.54 # 1
Node Clustering IMDb MAGNN ARI 16.74 # 1
NMI 0.1558 # 1
Link Prediction Last.FM MAGNN AP 98.93 # 1
AUC 98.91 # 1