Thomas N. Kipf

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)
Knowledge bases play a crucial role in many applications, for example question answering and information retrieval. Despite the great effort invested in creating and maintaining them, even the largest representatives (e.g., Yago, DBPedia or Wikidata) are highly incomplete. We introduce relational graph convolutional networks (R-GCNs) and apply them to two(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)
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 autoencoder (VGAE), a framework for unsupervised learning on graph-structured data based on the variational(More)
  • 1