A0517
Title: Phylogenetic latent position model for populations of networks
Authors: Federico Pavone - Université Paris Dauphine-PSL (France) [presenting]
Abstract: In many applications, networks are characterized by a hierarchical or multiresolution organization of the nodes responsible for the connectivity. A phylogenetic latent position model is proposed that effectively learns the multiresolution structure via modelling the latent positions as realizations of a branching process on a phylogenetic tree. The model is applied to the problem of learning the underlying structure responsible for the connectivity patterns in the human brain. A population of networks is analyzed to represent the brain's structural connectivity for a set of subjects. The model reveals a tree organization of the brain regions coherent with known hemisphere and lobe partitions. Such a result uncovers interesting new possible clustering of the brain regions at different levels of resolution.
