Variational Graph Auto-Encoders

21 Nov 2016  ·  Thomas N. Kipf, Max Welling ·

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.

PDF Abstract

Results from the Paper

 Ranked #1 on Link Prediction on Pubmed (ACC metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Graph Clustering Citeseer GAE ACC 40.8 # 8
Link Prediction Citeseer Variational graph auto-encoders ACC 91.4 # 1
Graph Clustering Cora GAE ACC 59.6 # 8
Link Prediction Cora Variational graph auto-encoders ACC 92.0 # 1
Link Prediction Pubmed Variational graph auto-encoders ACC 97.1 # 1
Graph Clustering Pubmed VGAE ACC 65.48 # 6