Semi-Supervised Classification with Graph Convolutional Networks
Thomas Kipf, Max Welling · arXiv (Cornell University) · 2016
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.
Cited by 7,431 works. doi:10.48550/arxiv.1609.02907 Open-access PDF
Authors
References
- Deep Residual Learning for Image Recognition
- AutoResearch Lite: a reproducible paper-inspired experiment runner (Adam mechanism reproduction and convergence-speed comparison)
- Dropout: a simple way to prevent neural networks from overfitting
- Visualizing Data using t-SNE
- Transductive Inference for Text Classification using Support Vector Machines
- node2vec
- The Graph Neural Network Model
- Advances In Deep Learning On Graphs (Gsp'18 Workshop)
- Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples
- Toward an Architecture for Never-Ending Language Learning