Variational Graph Auto-Encoders

Code

• github.com/tkipf/gae
  Officialtf★ 0
• github.com/pygod-team/pygod
  pytorch★ 1,482
• github.com/DaehanKim/vgae_pytorch
  pytorch★ 420
• github.com/deezer/linear_graph_autoencoders
  tf★ 136
• github.com/lfhase/ciga
  pytorch★ 121
• github.com/xiyou3368/DGVAE
  tf★ 26
• github.com/qkrdmsghk/GOODHSE
  pytorch★ 14
• github.com/jjzgeeks/vgae-based_model_poisoning_attack_fl
  pytorch★ 4
• github.com/Monti03/LinkPredictionOverClusters
  tf★ 0
• github.com/fleverest/gravity_graph_autoencoders
  tf★ 0

Abstract

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.

Tasks

Benchmark Results

Reproductions