A Collaborative Neurodynamic Approach to Multiobjective Optimization

A Collaborative Neurodynamic Approach to Multiobjective Optimization. Leung, M. & Wang, J. IEEE Transactions on Neural Networks and Learning Systems, 29(11):5738–5748, November, 2018.

Paper doi abstract bibtex

There are two ultimate goals in multiobjective optimization. The primary goal is to obtain a set of Paretooptimal solutions while the secondary goal is to obtain evenly distributed solutions to characterize the efﬁcient frontier. In this paper, a collaborative neurodynamic approach to multiobjective optimization is presented to attain both goals of Pareto optimality and solution diversity. The multiple objectives are ﬁrst scalarized using a weighted Chebyshev function. Multiple projection neural networks are employed to search for Pareto-optimal solutions with the help of a particle swarm optimization (PSO) algorithm in reintialization. To diversify the Pareto-optimal solutions, a holistic approach is proposed by maximizing the hypervolume (HV) using again a PSO algorithm. The experimental results show that the proposed approach outperforms three other state-ofthe-art multiobjective algorithms (i.e., HMOEA/D, MOEA/DD, and NSGAIII) most of times on 37 benchmark datasets in terms of HV and inverted generational distance.

@article{leung_collaborative_2018,
	title = {A {Collaborative} {Neurodynamic} {Approach} to {Multiobjective} {Optimization}},
	volume = {29},
	issn = {2162-237X, 2162-2388},
	url = {https://ieeexplore.ieee.org/document/8327871/},
	doi = {10.1109/tnnls.2018.2806481},
	abstract = {There are two ultimate goals in multiobjective optimization. The primary goal is to obtain a set of Paretooptimal solutions while the secondary goal is to obtain evenly distributed solutions to characterize the efﬁcient frontier. In this paper, a collaborative neurodynamic approach to multiobjective optimization is presented to attain both goals of Pareto optimality and solution diversity. The multiple objectives are ﬁrst scalarized using a weighted Chebyshev function. Multiple projection neural networks are employed to search for Pareto-optimal solutions with the help of a particle swarm optimization (PSO) algorithm in reintialization. To diversify the Pareto-optimal solutions, a holistic approach is proposed by maximizing the hypervolume (HV) using again a PSO algorithm. The experimental results show that the proposed approach outperforms three other state-ofthe-art multiobjective algorithms (i.e., HMOEA/D, MOEA/DD, and NSGAIII) most of times on 37 benchmark datasets in terms of HV and inverted generational distance.},
	language = {en},
	number = {11},
	urldate = {2022-01-20},
	journal = {IEEE Transactions on Neural Networks and Learning Systems},
	author = {Leung, Man-Fai and Wang, Jun},
	month = nov,
	year = {2018},
	keywords = {/unread},
	pages = {5738--5748},
}

Downloads: 0

{"_id":"mNLSQBs6xqQSyB9BT","bibbaseid":"leung-wang-acollaborativeneurodynamicapproachtomultiobjectiveoptimization-2018","author_short":["Leung, M.","Wang, J."],"bibdata":{"bibtype":"article","type":"article","title":"A Collaborative Neurodynamic Approach to Multiobjective Optimization","volume":"29","issn":"2162-237X, 2162-2388","url":"https://ieeexplore.ieee.org/document/8327871/","doi":"10.1109/tnnls.2018.2806481","abstract":"There are two ultimate goals in multiobjective optimization. The primary goal is to obtain a set of Paretooptimal solutions while the secondary goal is to obtain evenly distributed solutions to characterize the efﬁcient frontier. In this paper, a collaborative neurodynamic approach to multiobjective optimization is presented to attain both goals of Pareto optimality and solution diversity. The multiple objectives are ﬁrst scalarized using a weighted Chebyshev function. Multiple projection neural networks are employed to search for Pareto-optimal solutions with the help of a particle swarm optimization (PSO) algorithm in reintialization. To diversify the Pareto-optimal solutions, a holistic approach is proposed by maximizing the hypervolume (HV) using again a PSO algorithm. The experimental results show that the proposed approach outperforms three other state-ofthe-art multiobjective algorithms (i.e., HMOEA/D, MOEA/DD, and NSGAIII) most of times on 37 benchmark datasets in terms of HV and inverted generational distance.","language":"en","number":"11","urldate":"2022-01-20","journal":"IEEE Transactions on Neural Networks and Learning Systems","author":[{"propositions":[],"lastnames":["Leung"],"firstnames":["Man-Fai"],"suffixes":[]},{"propositions":[],"lastnames":["Wang"],"firstnames":["Jun"],"suffixes":[]}],"month":"November","year":"2018","keywords":"/unread","pages":"5738–5748","bibtex":"@article{leung_collaborative_2018,\n\ttitle = {A {Collaborative} {Neurodynamic} {Approach} to {Multiobjective} {Optimization}},\n\tvolume = {29},\n\tissn = {2162-237X, 2162-2388},\n\turl = {https://ieeexplore.ieee.org/document/8327871/},\n\tdoi = {10.1109/tnnls.2018.2806481},\n\tabstract = {There are two ultimate goals in multiobjective optimization. The primary goal is to obtain a set of Paretooptimal solutions while the secondary goal is to obtain evenly distributed solutions to characterize the efﬁcient frontier. In this paper, a collaborative neurodynamic approach to multiobjective optimization is presented to attain both goals of Pareto optimality and solution diversity. The multiple objectives are ﬁrst scalarized using a weighted Chebyshev function. Multiple projection neural networks are employed to search for Pareto-optimal solutions with the help of a particle swarm optimization (PSO) algorithm in reintialization. To diversify the Pareto-optimal solutions, a holistic approach is proposed by maximizing the hypervolume (HV) using again a PSO algorithm. The experimental results show that the proposed approach outperforms three other state-ofthe-art multiobjective algorithms (i.e., HMOEA/D, MOEA/DD, and NSGAIII) most of times on 37 benchmark datasets in terms of HV and inverted generational distance.},\n\tlanguage = {en},\n\tnumber = {11},\n\turldate = {2022-01-20},\n\tjournal = {IEEE Transactions on Neural Networks and Learning Systems},\n\tauthor = {Leung, Man-Fai and Wang, Jun},\n\tmonth = nov,\n\tyear = {2018},\n\tkeywords = {/unread},\n\tpages = {5738--5748},\n}\n\n","author_short":["Leung, M.","Wang, J."],"key":"leung_collaborative_2018","id":"leung_collaborative_2018","bibbaseid":"leung-wang-acollaborativeneurodynamicapproachtomultiobjectiveoptimization-2018","role":"author","urls":{"Paper":"https://ieeexplore.ieee.org/document/8327871/"},"keyword":["/unread"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/victorjhu","dataSources":["CmHEoydhafhbkXXt5"],"keywords":["/unread"],"search_terms":["collaborative","neurodynamic","approach","multiobjective","optimization","leung","wang"],"title":"A Collaborative Neurodynamic Approach to Multiobjective Optimization","year":2018}