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

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.

AAAI Conference on Artificial Intelligence (AAAI 2020)

References in corpus (3)

• Graph Neural Networks: A Review of Methods and Applications
• Interaction Networks for Learning about Objects, Relations and Physics
• Max-Margin Nonparametric Latent Feature Models for Link Prediction

Cited by in corpus (10)

• Self-supervised Learning on Graphs: Deep Insights and New Direction
• When Does Self-Supervision Help Graph Convolutional Networks?
• Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation
• Understanding and Resolving Performance Degradation in Graph Convolutional Networks
• Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training
• Socially-Aware Self-Supervised Tri-Training for Recommendation
• Self-supervised Graph Neural Networks without explicit negative sampling
• Leveraging Meta-path Contexts for Classification in Heterogeneous Information Networks
• RRLFSOR: An Efficient Self-Supervised Learning Strategy of Graph Convolutional Networks
• GAHNE: Graph-Aggregated Heterogeneous Network Embedding