Semi-Supervised Classification with Graph Convolutional Networks
This work addresses the problem of semi-supervised classification for graph data, such as citation networks, by introducing a novel and efficient method that scales linearly with graph edges.
The paper tackles semi-supervised learning on graph-structured data by proposing a scalable graph convolutional network based on a localized first-order approximation of spectral graph convolutions, achieving significant performance improvements over related methods in experiments on citation and knowledge graph datasets.
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.