Predict then Propagate: Graph Neural Networks meet Personalized PageRankDownload PDF

Published: 21 Dec 2018, Last Modified: 05 May 2023ICLR 2019 Conference Blind SubmissionReaders: Everyone
Abstract: 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.
Keywords: Graph, GCN, GNN, Neural network, Graph neural network, Message passing neural network, Semi-supervised classification, Semi-supervised learning, PageRank, Personalized PageRank
TL;DR: Personalized propagation of neural predictions (PPNP) improves graph neural networks by separating them into prediction and propagation via personalized PageRank.
Code: [![github](/images/github_icon.svg) klicperajo/ppnp](https://github.com/klicperajo/ppnp) + [![Papers with Code](/images/pwc_icon.svg) 4 community implementations](https://paperswithcode.com/paper/?openreview=H1gL-2A9Ym)
Data: [Chameleon(60%/20%/20% random splits)](https://paperswithcode.com/dataset/chameleon-60-20-20-random-splits-1), [Citeseer](https://paperswithcode.com/dataset/citeseer), [Cora](https://paperswithcode.com/dataset/cora), [Cornell (60%/20%/20% random splits)](https://paperswithcode.com/dataset/cornell-60-20-20-random-splits), [Deezer-Europe](https://paperswithcode.com/dataset/deezer-europe-1), [Film (60%/20%/20% random splits)](https://paperswithcode.com/dataset/film-60-20-20-random-splits), [Penn94](https://paperswithcode.com/dataset/penn94), [PubMed (60%/20%/20% random splits)](https://paperswithcode.com/dataset/pubmed-60-20-20-random-splits), [Pubmed](https://paperswithcode.com/dataset/pubmed), [Squirrel (60%/20%/20% random splits)](https://paperswithcode.com/dataset/squirrel-60-20-20-random-splits), [Texas(60%/20%/20% random splits)](https://paperswithcode.com/dataset/texas-60-20-20-random-splits-1), [Wisconsin(60%/20%/20% random splits)](https://paperswithcode.com/dataset/wisconsin-60-20-20-random-splits-1), [genius](https://paperswithcode.com/dataset/genius), [twitch-gamers](https://paperswithcode.com/dataset/twitch-gamers)
19 Replies

Loading