Variational Graph Auto-Encoders

By Thomas Kipf, Max Welling. 2016

4,397 citations recorded by the source corpus.

We introduce the variational graph auto-encoder (VGAE), a framework for unsupervised learning on graph-structured data based on the variational auto-encoder (VAE). This model makes use of latent variables and is capable of learning interpretable latent representations for undirected graphs. We demonstrate this model using a graph convolutional network (GCN) encoder and a simple inner product decoder. Our model achieves competitive results on a link prediction task in citation networks. In contrast to most existing models for unsupervised learning on graph-structured data and link prediction, our model can naturally incorporate node features, which significantly improves predictive performance on a number of benchmark datasets.

Subfields: Artificial Intelligence, Molecular Biology, Statistical and Nonlinear Physics, Generative Models, 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. Yoshua Bengio
  2. Jure Leskovec
  3. Mohit Bansal
  4. Percy Liang
  5. Sergey Levine
  6. William L. Hamilton
  7. Jianfeng Gao
  8. Philip S. Yu

In Molecular Biology

  1. William L. Hamilton
  2. Jure Leskovec
  3. Stephan Günnemann
  4. Rex Ying
  5. Aleksandar Bojchevski
  6. Marinka Zitnik
  7. Jian Tang
  8. Jiaxuan You

In Statistical and Nonlinear Physics

  1. Jure Leskovec
  2. William L. Hamilton
  3. Stephan Günnemann
  4. Shirui Pan
  5. Chengqi Zhang
  6. Bernhard Schölkopf
  7. Rex Ying
  8. Stefano Ermon

In Generative Models

  1. Stefano Ermon
  2. William L. Hamilton
  3. Arash Vahdat
  4. Max Welling
  5. Diederik P. Kingma
  6. Yoshua Bengio
  7. Jun Zhu
  8. Yang Song

In Graph Learning

  1. William L. Hamilton
  2. Jure Leskovec
  3. Stephan Günnemann
  4. Matthias Fey
  5. Rex Ying
  6. Aleksandar Bojchevski
  7. Marinka Zitnik
  8. Jian Tang

Citations in the corpus