![]() How powerful are Graph Convolutional Networks? Recent literature If you're already familiar with GCNs and related methods, you might want to jump directly to Embedding the karate club network. GCNs as differentiable generalization of the Weisfeiler-Lehman algorithm.Demo: Graph embeddings with a simple 1st-order GCN model.Spectral graph convolutions and Graph Convolutional Networks (GCNs).Short introduction to neural network models on graphs.I wrote a short comment on Ferenc's review here (at the very end of this post). (NIPS 2016), Convolutional Neural Networks on Graphs with Fast Localized Spectral FilteringĪnd a review/discussion post by Ferenc Huszar: How powerful are Graph Convolutions? that discusses some limitations of these kinds of models. Kipf & Welling (ICLR 2017), Semi-Supervised Classification with Graph Convolutional Networks (disclaimer: I'm the first author).The discussion here will mainly focus on two recent papers: ![]() ![]() In this post, I will give a brief overview of recent developments in this field and point out strengths and drawbacks of various approaches. In the last couple of years, a number of papers re-visited this problem of generalizing neural networks to work on arbitrarily structured graphs ( Bruna et al., ICLR 2014 Henaff et al., 2015 Duvenaud et al., NIPS 2015 Li et al., ICLR 2016 Defferrard et al., NIPS 2016 Kipf & Welling, ICLR 2017), some of them now achieving very promising results in domains that have previously been dominated by, e.g., kernel-based methods, graph-based regularization techniques and others. Yet, until recently, very little attention has been devoted to the generalization of neural network models to such structured datasets. Many important real-world datasets come in the form of graphs or networks: social networks, knowledge graphs, protein-interaction networks, the World Wide Web, etc. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |