Cross-view Self-Supervised Learning on Heterogeneous Graph Neural Network via Bootstrapping. (arXiv:2201.03340v2 [cs.LG] UPDATED)

Heterogeneous graph neural networks can represent information of
heterogeneous graphs with excellent ability. Recently, self-supervised learning
manner is researched which learns the unique expression of a graph through a
contrastive learning method. In the absence of labels, this learning methods
show great potential. However, contrastive learning relies heavily on positive
and negative pairs, and generating high-quality pairs from heterogeneous graphs
is difficult. In this paper, in line with recent innovations in self-supervised
learning called BYOL or bootstrapping, we introduce a …

arxiv bootstrapping graph learning network neural network self-supervised learning supervised learning