Predict then Propagate: Graph Neural Networks meet Personalized PageRank

ICLR 2019 Johannes KlicperaAleksandar BojchevskiStephan Günnemann

Neural message passing algorithms for semi-supervised classification on graphs have recently achieved great success. However, for classifying a node these methods only consider nodes that are a few propagation steps away and the size of this utilized neighborhood is hard to extend... (read more)

PDF Abstract

Evaluation results from the paper

Task Dataset Model Metric name Metric value Global rank Uses extra
training data
Node Classification MS ACADEMIC APPNP Accuracy 93.27% # 1