Representation Learning for Attributed Multiplex Heterogeneous Network

5 May 2019 Yukuo Cen Xu Zou Jianwei Zhang Hongxia Yang Jingren Zhou Jie Tang

Network embedding (or graph embedding) has been widely used in many real-world applications. However, existing methods mainly focus on networks with single-typed nodes/edges and cannot scale well to handle large networks... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Link Prediction Alibaba GATNE-I F1-Score 89.94 # 1
PR AUC 95.04 # 1
ROC AUC 84.2 # 1
Link Prediction Alibaba-S GATNE-T F1-Score 62.48 # 1
PR AUC 67.55 # 1
ROC AUC 66.71 # 1
Link Prediction Amazon GATNE-T F1-Score 92.87 # 1
PR AUC 97.05 # 1
ROC AUC 97.44 # 1
Link Prediction Twitter GATNE-T F1-Score 84.96 # 1
PR AUC 91.77 # 1
ROC AUC 92.3 # 1
Link Prediction YouTube GATNE-T F1-Score 76.83 # 1
PR AUC 81.93 # 1
ROC AUC 84.61 # 1

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