Predict then Propagate: Graph Neural Networks meet Personalized PageRank

By Johannes Klicpera, Aleksandar Bojchevski, Stephan Günnemann. 2018

2,108 citations recorded by the source corpus.

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. Our implementation is available online.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics, Information Retrieval & Search, Graph Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Stephan Günnemann
  2. Jure Leskovec
  3. William L. Hamilton
  4. Xiangnan He
  5. Marinka Zitnik
  6. Philip S. Yu
  7. Shirui Pan
  8. Michael M. Bronstein

In Statistical and Nonlinear Physics

  1. Stephan Günnemann
  2. Matthias Fey
  3. Jure Leskovec
  4. Michael M. Bronstein
  5. William L. Hamilton
  6. Xiyuan Wang
  7. Muhan Zhang
  8. Pan Li

In Information Retrieval & Search

  1. Stephan Günnemann
  2. Daniel Zügner
  3. Matthias Fey
  4. William L. Hamilton
  5. Muhan Zhang
  6. Hao Zhu
  7. Pan Li
  8. Xiyuan Wang

In Graph Learning

  1. Stephan Günnemann
  2. William L. Hamilton
  3. Jure Leskovec
  4. Matthias Fey
  5. Marinka Zitnik
  6. Michael M. Bronstein
  7. Aleksandar Bojchevski
  8. Pan Li

Citations in the corpus