Self-Supervised Learning of Graph Neural Networks: A Unified Review

Deep models trained in supervised mode have achieved remarkable success on a variety of tasks. When labeled samples are limited, self-supervised learning (SSL) is emerging as a new paradigm for making use of large amounts of unlabeled samples. SSL has achieved promising performance on natural language and image learning tasks. Recently, there is a trend to extend such success to graph data using graph neural networks (GNNs). In this survey, we provide a unified review of different ways of training GNNs using SSL. Specifically, we categorize SSL methods into contrastive and predictive models. In either category, we provide a unified framework for methods as well as how these methods differ in each component…

• NS
  National Science Foundation

  Awards: 2028361, DBI-2028361, CAREER, IIS-2006861, 2006861
• NI
  National Institutes of Health

  Award: 1R21NS102828
• NS
  National Science Foundation of Sri Lanka

  Awards: DBI-2028361, IIS-2006861