Clustering and inference for very sparse diverse multiplex networks.

Music City Center 

The talk considers the DIverse MultiPLEx Generalized Random Dot Product Graph (DIMPLE-GRDPG) network model
where all layers of the network have the same collection of nodes and follow the Generalized Random Dot Product Graph (GRDPG) model. In addition, all layers can be partitioned into groups such that the layers in the same group are embedded in the same ambient subspace but otherwise all matrices of connection probabilities can be different. While this is already a very difficult model, in addition we assume that layers of the network are very sparse. We shall use tensor-based approaches to recovery of the groups of layers in such network and subsequent estimation of the ambient subspaces.

Random network

Clustering

Tensor