Learn More
We present a scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs. We motivate the choice of our convolutional architecture via a localized first-order approximation of spectral graph convolutions. Our model scales linearly in the(More)
1 A latent variable model for graph-structured data Figure 1: Latent space of unsupervised VGAE model trained on Cora citation network dataset [1]. Grey lines denote citation links. Colors denote document class (not provided during training). Best viewed on screen. We introduce the variational graph auto-encoder (VGAE), a framework for unsupervised learning(More)
  • 1