Semi-Supervised Classification with Graph Convolutional Networks

Code

• github.com/tkipf/pygcn
  Officialpytorch★ 5,397
• github.com/IllinoisGraphBenchmark/IGB-Datasets
  pytorch★ 86
• github.com/tk-rusch/graphcon
  pytorch★ 60
• github.com/mahsa91/RA-GCN
  pytorch★ 25
• github.com/fanzhenliu/dagad
  pytorch★ 21
• github.com/nnaakkaaii/g2-MLP
  pytorch★ 10
• github.com/basiralab/reproduciblefedgnn
  pytorch★ 9
• github.com/basiralab/RG-Select
  pytorch★ 9
• github.com/mahsa91/GKD
  pytorch★ 6
• github.com/selmiss/gp-tlstgcn
  pytorch★ 4

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.

Tasks

Benchmark Results

Reproductions