Inference on networks
Complex interacting systems are often represented by large datasets containing a considerable amount of information. The question is how to capture the relevant macroscopic behavior by retaining only a small amount of information. This can be formalized as an inference problem where we want to extract a set of model parameters capable of describing the observed system and making future predictions.
In particular, I am interested in analyzing systems where elements interact in multiple ways, as in multilayer networks, and systems displaying hidden hierarchies that might play a role in determining the interaction patterns that we observe.
- Community detection with node attributes in multilayer networks
- Sampling on networks: estimating spectral centrality measures and their impact in evaluating other relevant network measures
- Sampling on Networks: Estimating Eigenvector Centrality on Incomplete Networks
- A physical model for efficient ranking in networks
- Are `Water Smart Landscapes' Contagious? An epidemic approach on networks to study peer effects