Semi-Supervised Classification with Graph Convolutional Networks

By Thomas N. Kipf et al.

Published on Feb. 22, 2017

Read the original document by opening this link in a new tab.

Table of Contents

1. Introduction
2. Fast Approximate Convolutions on Graphs
3. Semi-Supervised Node Classification
4. Related Work
5. Experiments

Summary

The document presents a scalable approach for semi-supervised learning on graph-structured data using graph convolutional networks. It introduces a simple and well-behaved layer-wise propagation rule for neural network models on graphs. The model demonstrates fast and scalable semi-supervised classification of nodes in a graph, outperforming related methods in terms of classification accuracy and efficiency. Experimental results on various datasets show the effectiveness of the proposed approach.