Hierarchical Contrastive Learning Enhanced Heterogeneous Graph Neural Network

arXiv:2304.12228v2 Announce Type: replace
Abstract: Heterogeneous graph neural networks (HGNNs) as an emerging technique have shown superior capacity of dealing with heterogeneous information network (HIN). However, most HGNNs follow a semi-supervised learning manner, which notably limits their wide use in reality since labels are usually scarce in real applications. Recently, contrastive learning, a self-supervised method, becomes one of the most exciting learning paradigms and shows great potential when there are no labels. In this paper, we study the problem of …

abstract applications arxiv capacity cs.lg graph graph neural network graph neural networks hierarchical information labels network networks neural network neural networks reality semi-supervised semi-supervised learning supervised learning type