A Two-Level Transfer Learning Algorithm for Evolutionary Multitasking
Different from conventional single-task optimization, the recently proposed multitasking optimization (MTO) simultaneously deals with multiple optimization tasks with different types of decision variables. MTO explores the underlying similarity and complementarity among the component tasks to improv...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2020-01-01
|
| Series: | Frontiers in Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fnins.2019.01408/full |
| _version_ | 1831725036273139712 |
|---|---|
| author | Xiaoliang Ma Xiaoliang Ma Xiaoliang Ma Qunjian Chen Qunjian Chen Qunjian Chen Yanan Yu Yanan Yu Yanan Yu Yiwen Sun Lijia Ma Lijia Ma Lijia Ma Zexuan Zhu Zexuan Zhu Zexuan Zhu |
| author_facet | Xiaoliang Ma Xiaoliang Ma Xiaoliang Ma Qunjian Chen Qunjian Chen Qunjian Chen Yanan Yu Yanan Yu Yanan Yu Yiwen Sun Lijia Ma Lijia Ma Lijia Ma Zexuan Zhu Zexuan Zhu Zexuan Zhu |
| author_sort | Xiaoliang Ma |
| collection | DOAJ |
| description | Different from conventional single-task optimization, the recently proposed multitasking optimization (MTO) simultaneously deals with multiple optimization tasks with different types of decision variables. MTO explores the underlying similarity and complementarity among the component tasks to improve the optimization process. The well-known multifactorial evolutionary algorithm (MFEA) has been successfully introduced to solve MTO problems based on transfer learning. However, it uses a simple and random inter-task transfer learning strategy, thereby resulting in slow convergence. To deal with this issue, this paper presents a two-level transfer learning (TLTL) algorithm, in which the upper-level implements inter-task transfer learning via chromosome crossover and elite individual learning, and the lower-level introduces intra-task transfer learning based on information transfer of decision variables for an across-dimension optimization. The proposed algorithm fully uses the correlation and similarity among the component tasks to improve the efficiency and effectiveness of MTO. Experimental studies demonstrate the proposed algorithm has outstanding ability of global search and fast convergence rate. |
| first_indexed | 2024-12-21T04:33:57Z |
| format | Article |
| id | doaj.art-6187ec6e507541ed96b044c32cdfb928 |
| institution | Directory Open Access Journal |
| issn | 1662-453X |
| language | English |
| last_indexed | 2024-12-21T04:33:57Z |
| publishDate | 2020-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroscience |
| spelling | doaj.art-6187ec6e507541ed96b044c32cdfb9282022-12-21T19:15:54ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2020-01-011310.3389/fnins.2019.01408493604A Two-Level Transfer Learning Algorithm for Evolutionary MultitaskingXiaoliang Ma0Xiaoliang Ma1Xiaoliang Ma2Qunjian Chen3Qunjian Chen4Qunjian Chen5Yanan Yu6Yanan Yu7Yanan Yu8Yiwen Sun9Lijia Ma10Lijia Ma11Lijia Ma12Zexuan Zhu13Zexuan Zhu14Zexuan Zhu15College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, ChinaGuangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen University, Shenzhen, ChinaNational Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, ChinaCollege of Computer Science and Software Engineering, Shenzhen University, Shenzhen, ChinaGuangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen University, Shenzhen, ChinaNational Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, ChinaCollege of Computer Science and Software Engineering, Shenzhen University, Shenzhen, ChinaGuangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen University, Shenzhen, ChinaNational Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, ChinaSchool of Medicine, Shenzhen University, Shenzhen, ChinaCollege of Computer Science and Software Engineering, Shenzhen University, Shenzhen, ChinaGuangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen University, Shenzhen, ChinaNational Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, ChinaCollege of Computer Science and Software Engineering, Shenzhen University, Shenzhen, ChinaGuangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen University, Shenzhen, ChinaNational Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, ChinaDifferent from conventional single-task optimization, the recently proposed multitasking optimization (MTO) simultaneously deals with multiple optimization tasks with different types of decision variables. MTO explores the underlying similarity and complementarity among the component tasks to improve the optimization process. The well-known multifactorial evolutionary algorithm (MFEA) has been successfully introduced to solve MTO problems based on transfer learning. However, it uses a simple and random inter-task transfer learning strategy, thereby resulting in slow convergence. To deal with this issue, this paper presents a two-level transfer learning (TLTL) algorithm, in which the upper-level implements inter-task transfer learning via chromosome crossover and elite individual learning, and the lower-level introduces intra-task transfer learning based on information transfer of decision variables for an across-dimension optimization. The proposed algorithm fully uses the correlation and similarity among the component tasks to improve the efficiency and effectiveness of MTO. Experimental studies demonstrate the proposed algorithm has outstanding ability of global search and fast convergence rate.https://www.frontiersin.org/article/10.3389/fnins.2019.01408/fullevolutionary multitaskingmultifactorial optimizationtransfer learningmemetic algorithmknowledge transfer |
| spellingShingle | Xiaoliang Ma Xiaoliang Ma Xiaoliang Ma Qunjian Chen Qunjian Chen Qunjian Chen Yanan Yu Yanan Yu Yanan Yu Yiwen Sun Lijia Ma Lijia Ma Lijia Ma Zexuan Zhu Zexuan Zhu Zexuan Zhu A Two-Level Transfer Learning Algorithm for Evolutionary Multitasking Frontiers in Neuroscience evolutionary multitasking multifactorial optimization transfer learning memetic algorithm knowledge transfer |
| title | A Two-Level Transfer Learning Algorithm for Evolutionary Multitasking |
| title_full | A Two-Level Transfer Learning Algorithm for Evolutionary Multitasking |
| title_fullStr | A Two-Level Transfer Learning Algorithm for Evolutionary Multitasking |
| title_full_unstemmed | A Two-Level Transfer Learning Algorithm for Evolutionary Multitasking |
| title_short | A Two-Level Transfer Learning Algorithm for Evolutionary Multitasking |
| title_sort | two level transfer learning algorithm for evolutionary multitasking |
| topic | evolutionary multitasking multifactorial optimization transfer learning memetic algorithm knowledge transfer |
| url | https://www.frontiersin.org/article/10.3389/fnins.2019.01408/full |
| work_keys_str_mv | AT xiaoliangma atwoleveltransferlearningalgorithmforevolutionarymultitasking AT xiaoliangma atwoleveltransferlearningalgorithmforevolutionarymultitasking AT xiaoliangma atwoleveltransferlearningalgorithmforevolutionarymultitasking AT qunjianchen atwoleveltransferlearningalgorithmforevolutionarymultitasking AT qunjianchen atwoleveltransferlearningalgorithmforevolutionarymultitasking AT qunjianchen atwoleveltransferlearningalgorithmforevolutionarymultitasking AT yananyu atwoleveltransferlearningalgorithmforevolutionarymultitasking AT yananyu atwoleveltransferlearningalgorithmforevolutionarymultitasking AT yananyu atwoleveltransferlearningalgorithmforevolutionarymultitasking AT yiwensun atwoleveltransferlearningalgorithmforevolutionarymultitasking AT lijiama atwoleveltransferlearningalgorithmforevolutionarymultitasking AT lijiama atwoleveltransferlearningalgorithmforevolutionarymultitasking AT lijiama atwoleveltransferlearningalgorithmforevolutionarymultitasking AT zexuanzhu atwoleveltransferlearningalgorithmforevolutionarymultitasking AT zexuanzhu atwoleveltransferlearningalgorithmforevolutionarymultitasking AT zexuanzhu atwoleveltransferlearningalgorithmforevolutionarymultitasking AT xiaoliangma twoleveltransferlearningalgorithmforevolutionarymultitasking AT xiaoliangma twoleveltransferlearningalgorithmforevolutionarymultitasking AT xiaoliangma twoleveltransferlearningalgorithmforevolutionarymultitasking AT qunjianchen twoleveltransferlearningalgorithmforevolutionarymultitasking AT qunjianchen twoleveltransferlearningalgorithmforevolutionarymultitasking AT qunjianchen twoleveltransferlearningalgorithmforevolutionarymultitasking AT yananyu twoleveltransferlearningalgorithmforevolutionarymultitasking AT yananyu twoleveltransferlearningalgorithmforevolutionarymultitasking AT yananyu twoleveltransferlearningalgorithmforevolutionarymultitasking AT yiwensun twoleveltransferlearningalgorithmforevolutionarymultitasking AT lijiama twoleveltransferlearningalgorithmforevolutionarymultitasking AT lijiama twoleveltransferlearningalgorithmforevolutionarymultitasking AT lijiama twoleveltransferlearningalgorithmforevolutionarymultitasking AT zexuanzhu twoleveltransferlearningalgorithmforevolutionarymultitasking AT zexuanzhu twoleveltransferlearningalgorithmforevolutionarymultitasking AT zexuanzhu twoleveltransferlearningalgorithmforevolutionarymultitasking |