Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning

Authors

  • Qimai Li The Hong Kong Polytechnic University
  • Zhichao Han ETH Zurich, The Hong Kong Polytechnic University
  • Xiao-ming Wu The Hong Kong Polytechnic University

Keywords:

graph convolutional networks, semi-supervised learning, deep learning, graph-based learning

Abstract

Many interesting problems in machine learning are being revisited with new deep learning tools. For graph-based semi-supervised learning, a recent important development is graph convolutional networks (GCNs), which nicely integrate local vertex features and graph topology in the convolutional layers. Although the GCN model compares favorably with other state-of-the-art methods, its mechanisms are not clear and it still requires considerable amount of labeled data for validation and model selection. In this paper, we develop deeper insights into the GCN model and address its fundamental limits. First, we show that the graph convolution of the GCN model is actually a special form of Laplacian smoothing, which is the key reason why GCNs work, but it also brings potential concerns of over-smoothing with many convolutional layers. Second, to overcome the limits of the GCN model with shallow architectures, we propose both co-training and self-training approaches to train GCNs. Our approaches significantly improve GCNs in learning with very few labels, and exempt them from requiring additional labels for validation. Extensive experiments on benchmarks have verified our theory and proposals.

Downloads

Published

2018-04-29

How to Cite

Li, Q., Han, Z., & Wu, X.- ming. (2018). Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11604