Variational Graph Auto-Encoders

by   Thomas Kipf, et al.
University of Amsterdam

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.


page 1

page 2

page 3


Effective Decoding in Graph Auto-Encoder using Triadic Closure

The (variational) graph auto-encoder and its variants have been popularl...

Directed Graph Auto-Encoders

We introduce a new class of auto-encoders for directed graphs, motivated...

A Deep Latent Space Model for Graph Representation Learning

Graph representation learning is a fundamental problem for modeling rela...

Barlow Graph Auto-Encoder for Unsupervised Network Embedding

Network embedding has emerged as a promising research field for network ...

Towards Conceptual Compression

We introduce a simple recurrent variational auto-encoder architecture th...

Spiking Variational Graph Auto-Encoders for Efficient Graph Representation Learning

Graph representation learning is a fundamental research issue and benefi...

Graphite: Iterative Generative Modeling of Graphs

Graphs are a fundamental abstraction for modeling relational data. Howev...

Code Repositories

Please sign up or login with your details

Forgot password? Click here to reset