Representation learning in multiplex graphs: Where and how to fuse information?

arXiv:2402.17906v1 Announce Type: new
Abstract: In recent years, unsupervised and self-supervised graph representation learning has gained popularity in the research community. However, most proposed methods are focused on homogeneous networks, whereas real-world graphs often contain multiple node and edge types. Multiplex graphs, a special type of heterogeneous graphs, possess richer information, provide better modeling capabilities and integrate more detailed data from potentially different sources. The diverse edge types in multiplex graphs provide more context and insights into the underlying processes …

abstract arxiv community cs.lg cs.si edge graph graph representation graphs information multiple networks node representation representation learning research research community type types unsupervised world