Graph_sampler: a simple tool for fully Bayesian analyses of DAG-models

TL;DR

Graph_sampler is a fast, free C software tool for Bayesian inference on DAGs, capable of handling various data types and priors, with improved sampling efficiency demonstrated on simulated and real networks.

Contribution

It introduces a new, faster Metropolis-Hastings kernel and provides a compact, efficient software for Bayesian network structure learning.

Findings

Demonstrated high performance on simulated data

Effective handling of continuous and discrete data

Versatile use of informative and uninformative priors

Abstract

Bayesian networks (BNs) are widely used graphical models usable to draw statistical inference about Directed acyclic graphs (DAGs). We presented here Graph_sampler a fast free C language software for structural inference on BNs. Graph_sampler uses a fully Bayesian approach in which the marginal likelihood of the data and prior information about the network structure are considered. This new software can handle both the continuous as well discrete data and based on the data type two different models are formulated. The software also provides a wide variety of structure priors which can be informative or uninformative. We proposed a new and much faster jumping kernel strategy in the Metropolis-Hastings algorithm. The source C code distributed is very compact, fast, uses low memory and disk storage. We performed out several analyses based on different simulated data sets and synthetic as well as real networks to discuss the performance of Graph_sampler.