Predict then Propagate: Graph Neural Networks meet Personalized PageRank

This page is about our paper

Predict then Propagate: Graph Neural Networks meet Personalized PageRank
by Johannes Gasteiger, Aleksandar Bojchevski and Stephan Günnemann
Published at the International Conference on Learning Representations (ICLR) 2019

Note that the author's name has changed from Johannes Klicpera to Johannes Gasteiger.


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. In this paper, we use the relationship between graph convolutional networks (GCN) and PageRank to derive an improved propagation scheme based on personalized PageRank. We utilize this propagation procedure to construct a simple model, personalized propagation of neural predictions (PPNP), and its fast approximation, APPNP. Our model's training time is on par or faster and its number of parameters on par or lower than previous models. It leverages a large, adjustable neighborhood for classification and can be easily combined with any neural network. We show that this model outperforms several recently proposed methods for semi-supervised classification in the most thorough study done so far for GCN-like models.


Please cite our paper if you use the model, experimental results, or our code in your own work:

title = {Predict then Propagate: Graph Neural Networks meet Personalized PageRank},
author = {Gasteiger, Johannes and Bojchevski, Aleksandar and G{\"u}nnemann, Stephan},
booktitle={International Conference on Learning Representations (ICLR)},
year = {2019}


[Paper | Poster | GitHub]