Hierarchical Graph Convolutional Networks for Semi-supervised Node Classification

13 Feb 2019Fenyu HuYanqiao ZhuShu WuLiang WangTieniu Tan

Graph convolutional networks (GCNs) have been successfully applied in node classification tasks of network mining. However, most of these models based on neighborhood aggregation are usually shallow and lack the "graph pooling" mechanism, which prevents the model from obtaining adequate global information... (read more)

PDF Abstract
Task Dataset Model Metric name Metric value Global rank Compare
Node Classification CiteSeer with Public Split: fixed 20 nodes per class H-GCN Accuracy 72.8% # 4
Node Classification Cora with Public Split: fixed 20 nodes per class H-GCN Accuracy 84.5% # 1
Node Classification PubMed with Public Split: fixed 20 nodes per class H-GCN Accuracy 79.8% # 2