Inproceedings,

Semi-Supervised Classification with Graph Convolutional Networks

, and .
Proceedings of the 5th International Conference on Learning Representations, (2017)

Abstract

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 number of graph edges and learns hidden layer representations that encode both local graph structure and features of nodes. In a number of experiments on citation networks and on a knowledge graph dataset we demonstrate that our approach outperforms related methods by a significant margin.

Tags

Users

  • @sxkdz
  • @tobias.koopmann
  • @lukas.heppel
  • @e.fischer
  • @tschumacher
  • @dblp
  • @nilsd

Comments and Reviewsshow / hide

  • @nilsd
    @nilsd 3 years ago
    Das Paper erklärt die Graph Convolution, welche ich in meiner Seminararbeit vorstelle.
Please log in to take part in the discussion (add own reviews or comments).