Jul 22, 2020 – 11:00 AM
Similarity network fusion is a tool that aggregates the information coming from a multiplex network into a unique layer through a cross diffusion process.
However, the process itself does not allow to infer which layer has the major impact in the determination of the topology of the resulting
In this talk, the use of distance correlation and, in turn, partial distance correlation is proposed for individuating which layer is the
most relevant in the determination of the final network structure. Finally, an application to networks of scholarly journals is presented.