Probabilistic Multilayer Networks

TL;DR

This paper introduces probabilistic multilayer networks derived from information-theoretic correlation measures, enabling formal probabilistic inference in complex multilayered systems with applications in biology and social sciences.

Contribution

It presents a novel framework for probabilistic multilayer networks based on correlation measures, with practical examples from genomics and social systems.

Findings

Effective modeling of biological and social multilayer systems

Demonstrated probabilistic inference on large datasets

Applied framework to real-world biological and social problems

Abstract

Here we introduce probabilistic weighted and unweighted multilayer networks as derived from information theoretical correlation measures on large multidimensional datasets. We present the fundamentals of the formal application of probabilistic inference on problems embedded in multilayered environments, providing examples taken from the analysis of biological and social systems: cancer genomics and drug-related violence.