A New Bayesian Network Structure Learning Algorithm Mechanism Based on the Decomposability of Scoring Functions

Guoliang LI; Lining XING; Zhongshan ZHANG; Yingwu CHEN

doi:10.1587/transfun.E100.A.1541

A New Bayesian Network Structure Learning Algorithm Mechanism Based on the Decomposability of Scoring Functions

Guoliang LI, Lining XING, Zhongshan ZHANG, Yingwu CHEN

Full Text Views

0

Share
Cite this

Summary :

Bayesian networks are a powerful approach for representation and reasoning under conditions of uncertainty. Of the many good algorithms for learning Bayesian networks from data, the bio-inspired search algorithm is one of the most effective. In this paper, we propose a hybrid mutual information-modified binary particle swarm optimization (MI-MBPSO) algorithm. This technique first constructs a network based on MI to improve the quality of the initial population, and then uses the decomposability of the scoring function to modify the BPSO algorithm. Experimental results show that, the proposed hybrid algorithm outperforms various other state-of-the-art structure learning algorithms.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E100-A No.7 pp.1541-1551

Publication Date: 2017/07/01

Publicized

Online ISSN: 1745-1337

DOI: 10.1587/transfun.E100.A.1541

Type of Manuscript: PAPER

Category: Graphs and Networks

Authors

Guoliang LI
  National University of Defense Technology
Lining XING
  National University of Defense Technology
Zhongshan ZHANG
  National University of Defense Technology
Yingwu CHEN
  National University of Defense Technology

Keyword

Bayesian network, structure learning, mutual information, the decomposability of score functions, binary particle swarm optimization

Cite this

Copy

Guoliang LI, Lining XING, Zhongshan ZHANG, Yingwu CHEN, "A New Bayesian Network Structure Learning Algorithm Mechanism Based on the Decomposability of Scoring Functions" in IEICE TRANSACTIONS on Fundamentals, vol. E100-A, no. 7, pp. 1541-1551, July 2017, doi: 10.1587/transfun.E100.A.1541.
Abstract: Bayesian networks are a powerful approach for representation and reasoning under conditions of uncertainty. Of the many good algorithms for learning Bayesian networks from data, the bio-inspired search algorithm is one of the most effective. In this paper, we propose a hybrid mutual information-modified binary particle swarm optimization (MI-MBPSO) algorithm. This technique first constructs a network based on MI to improve the quality of the initial population, and then uses the decomposability of the scoring function to modify the BPSO algorithm. Experimental results show that, the proposed hybrid algorithm outperforms various other state-of-the-art structure learning algorithms.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/transfun.E100.A.1541/_p

Copy

@ARTICLE{e100-a_7_1541,
author={Guoliang LI, Lining XING, Zhongshan ZHANG, Yingwu CHEN, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A New Bayesian Network Structure Learning Algorithm Mechanism Based on the Decomposability of Scoring Functions},
year={2017},
volume={E100-A},
number={7},
pages={1541-1551},
abstract={Bayesian networks are a powerful approach for representation and reasoning under conditions of uncertainty. Of the many good algorithms for learning Bayesian networks from data, the bio-inspired search algorithm is one of the most effective. In this paper, we propose a hybrid mutual information-modified binary particle swarm optimization (MI-MBPSO) algorithm. This technique first constructs a network based on MI to improve the quality of the initial population, and then uses the decomposability of the scoring function to modify the BPSO algorithm. Experimental results show that, the proposed hybrid algorithm outperforms various other state-of-the-art structure learning algorithms.},
keywords={},
doi={10.1587/transfun.E100.A.1541},
ISSN={1745-1337},
month={July},}

Copy

TY - JOUR
TI - A New Bayesian Network Structure Learning Algorithm Mechanism Based on the Decomposability of Scoring Functions
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1541
EP - 1551
AU - Guoliang LI
AU - Lining XING
AU - Zhongshan ZHANG
AU - Yingwu CHEN
PY - 2017
DO - 10.1587/transfun.E100.A.1541
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E100-A
IS - 7
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - July 2017
AB - Bayesian networks are a powerful approach for representation and reasoning under conditions of uncertainty. Of the many good algorithms for learning Bayesian networks from data, the bio-inspired search algorithm is one of the most effective. In this paper, we propose a hybrid mutual information-modified binary particle swarm optimization (MI-MBPSO) algorithm. This technique first constructs a network based on MI to improve the quality of the initial population, and then uses the decomposability of the scoring function to modify the BPSO algorithm. Experimental results show that, the proposed hybrid algorithm outperforms various other state-of-the-art structure learning algorithms.
ER -