A Hybrid Structure Learning Algorithm for Bayesian Network Using Experts' Knowledge.

Hongru Li,Huiping Guo

doi:10.3390/e20080620

Abstract

Bayesian network structure learning from data has been proved to be a NP-hard (Non-deterministic Polynomial-hard) problem. An effective method of improving the accuracy of Bayesian network structure is using experts’ knowledge instead of only using data. Some experts’ knowledge (named here explicit knowledge) can make the causal relationship between nodes in Bayesian Networks (BN) structure clear, while the others (named here vague knowledge) cannot. In the previous algorithms for BN structure learning, only the explicit knowledge was used, but the vague knowledge, which was ignored, is also valuable and often exists in the real world. Therefore we propose a new method of using more comprehensive experts’ knowledge based on hybrid structure learning algorithm, a kind of two-stage algorithm. Two types of experts’ knowledge are defined and incorporated into the hybrid algorithm. We formulate rules to generate better initial network structure and improve the scoring function. Furthermore, we take expert level difference and opinion conflict into account. Experimental results show that our proposed method can improve the structure learning performance.

Highlights

Bayesian networks (BN) is one of the most effective theoretical models for decision making, especially for uncertain knowledge reasoning [1]
Comparing with three cases ofexperts’ knowledge, we can see that learning with explicit knowledge and vague knowledge is better than learning with explicit knowledge alone
We introduce a new method of using explicit knowledge and vague knowledge based on a

Summary

Introduction

Bayesian networks (BN) is one of the most effective theoretical models for decision making, especially for uncertain knowledge reasoning [1]. Bayesian network learning consists of two parts, structure learning and parameter learning. Of these two parts, structure learning is the core part for Bayesian network learning. The second group of algorithms consider structure learning as a structural optimization problem, using a search strategy to select the structure with the highest score of a scoring function which measures the fitting degree of network and data. The major weakness of these algorithms is that they to fall into local optima. The third group of algorithms, Entropy 2018, 20, 620; doi:10.3390/e20080620 www.mdpi.com/journal/entropy

Methods

Results

Discussion

Conclusion