March 3, 2026

Learning Bayesian Network Structures Without Variable Ordering Influence: A Markov Blanket‐Based Approach

Key Points

The new DMBBN approach constructs graphs, effectively utilizing markov blankets to address structural discovery in bayesian networks.
In experiments involving large datasets, DMBBN shows promise by avoiding reliance on variable orderings and reducing complexity.
This graph-building method combines local structures induced by each variable's markov blanket without repeating nodes or forming cycles.
The proposed method highlights the potential for advancements in learning bayesian networks in complex datasets, indicating a need for further exploration.

Abstract

ABSTRACT Several methods in the literature address the discovery, from data, of a directed acyclic graph that is the structure of a Bayesian network. This is a challenging task, due to the combinatorial nature of the space of graphs, which grows exponentially with the number of variables. This paper proposes a new method to learn Bayesian network structures, based on Markov blankets. The proposed method, called DMBBN (Dynamic Markov Blanket Bayesian Network), builds a graph from a set of local structures that are induced based on the Markov blanket of each variable of interest. The local structures are combined to generate a single Bayesian network structure, without repetition of nodes and without cycles. The experiments carried out show that DMBBN is promising, especially in large datasets, as it does not depend on a prior ordering of the variables.

Bookmark

Learning Bayesian Network Structures Without Variable Ordering Influence: A Markov Blanket‐Based Approach

Key Points

Abstract

Cite This Study