Heterogeneous Graph Contrastive Learning with Meta-path Contexts and Adaptively Weighted Negative Samples

arXiv:2212.13847v3 Announce Type: replace
Abstract: Heterogeneous graph contrastive learning has received wide attention recently. Some existing methods use meta-paths, which are sequences of object types that capture semantic relationships between objects, to construct contrastive views. However, most of them ignore the rich meta-path context information that describes how two objects are connected by meta-paths. Further, they fail to distinguish negative samples, which could adversely affect the model performance. To address the problems, we propose MEOW, which considers both meta-path contexts …

abstract arxiv attention construct context cs.lg graph however information meta negative object objects path relationships samples semantic them type types