TY - JOUR
T1 - Analysis of Bayesian Network Learning Techniques for a Hybrid Multi-objective Bayesian Estimation of Distribution Algorithm
T2 - a case study on MNK Landscape
AU - Martins, Marcella S.R.
AU - El Yafrani, Mohamed
AU - Delgado, Myriam
AU - Lüders, Ricardo
AU - Santana, Roberto
AU - Siqueira, Hugo V.
AU - Akcay, Huseyin G.
AU - Ahiod, Belaïd
N1 - Funding Information:
M. Delgado acknowledges CNPq, grants 309935/2017-2 e 439226/2018-0. R. Santana acknowledges support by the TIN2016-78365-R (Spanish Ministry of Economy, Industry and Competitiveness), PID2019-104966GB-I00 (Spanish Ministry of Science and Innovation), the IT-1244-19 (Basque Government) program and project 3KIA (KK-2020/00049) funded by the SPRI-Basque Government through the ELKARTEK program.
Publisher Copyright:
© 2021, The Author(s), under exclusive licence to Springer Science+Business Media, LLC part of Springer Nature.
PY - 2021/8
Y1 - 2021/8
N2 - This work investigates different Bayesian network structure learning techniques by thoroughly studying several variants of Hybrid Multi-objective Bayesian Estimation of Distribution Algorithm (HMOBEDA), applied to the MNK Landscape combinatorial problem. In the experiments, we evaluate the performance considering three different aspects: optimization abilities, robustness and learning efficiency. Results for instances of multi- and many-objective MNK-landscape show that, score-based structure learning algorithms appear to be the best choice. In particular, HMOBEDAk2 was capable of producing results comparable with the other variants in terms of the runtime of convergence and the coverage of the final Pareto front, with the additional advantage of providing solutions that are less sensible to noise while the variability of the corresponding Bayesian network models is reduced.
AB - This work investigates different Bayesian network structure learning techniques by thoroughly studying several variants of Hybrid Multi-objective Bayesian Estimation of Distribution Algorithm (HMOBEDA), applied to the MNK Landscape combinatorial problem. In the experiments, we evaluate the performance considering three different aspects: optimization abilities, robustness and learning efficiency. Results for instances of multi- and many-objective MNK-landscape show that, score-based structure learning algorithms appear to be the best choice. In particular, HMOBEDAk2 was capable of producing results comparable with the other variants in terms of the runtime of convergence and the coverage of the final Pareto front, with the additional advantage of providing solutions that are less sensible to noise while the variability of the corresponding Bayesian network models is reduced.
KW - Estimation of distribution algorithms
KW - Many-objective optimization
KW - Robustness
KW - Structure learning techniques
UR - https://www.scopus.com/pages/publications/85100676007
U2 - 10.1007/s10732-021-09469-x
DO - 10.1007/s10732-021-09469-x
M3 - Journal article
AN - SCOPUS:85100676007
SN - 1381-1231
VL - 27
SP - 549
EP - 573
JO - Journal of Heuristics
JF - Journal of Heuristics
IS - 4
ER -