Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labeled Nodes

Authors

  • Ke Sun Peking University
  • Zhouchen Lin Peking University
  • Zhanxing Zhu Peking University

DOI:

https://doi.org/10.1609/aaai.v34i04.6048

Abstract

Graph Convolutional Networks (GCNs) play a crucial role in graph learning tasks, however, learning graph embedding with few supervised signals is still a difficult problem. In this paper, we propose a novel training algorithm for Graph Convolutional Network, called Multi-Stage Self-Supervised (M3S) Training Algorithm, combined with self-supervised learning approach, focusing on improving the generalization performance of GCNs on graphs with few labeled nodes. Firstly, a Multi-Stage Training Framework is provided as the basis of M3S training method. Then we leverage DeepCluster technique, a popular form of self-supervised learning, and design corresponding aligning mechanism on the embedding space to refine the Multi-Stage Training Framework, resulting in M3S Training Algorithm. Finally, extensive experimental results verify the superior performance of our algorithm on graphs with few labeled nodes under different label rates compared with other state-of-the-art approaches.

Downloads

Published

2020-04-03

How to Cite

Sun, K., Lin, Z., & Zhu, Z. (2020). Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labeled Nodes. Proceedings of the AAAI Conference on Artificial Intelligence, 34(04), 5892-5899. https://doi.org/10.1609/aaai.v34i04.6048

Issue

Section

AAAI Technical Track: Machine Learning