Abstract
Multi-task optimization is an emerging research topic in evolutionary computation, which aims to solve multiple optimization tasks simultaneously through knowledge transfer. However, existing multi-task evolutionary algorithms suffer from the re-evaluation problem, leading to unnecessary consumption of computing resources. To address this issue, a non-revisiting framework is proposed, which allows the non-revisiting scheme to be aided by historical information during the evolutionary search process. Moreover, an individual updating strategy is designed to improve the search efficiency of the algorithm and enhance the ability to escape local optima. Furthermore, a parallel scheme of the proposed framework is developedNational Frontiers Science Center for Industrial Intelligence and Systems Optimizationcomputation time on the CUDA architecture. To evaluate the effectiveness of the proposed framework, it is integrated with success-history based adaptive differential evolution. A comparative study of the proposed algorithm with eight state-of-the-art multi-task evolutionary algorithms is performed on nine benchmark problems. The experimental results demonstrate that the proposed algorithm outperforms the existing algorithms, highlighting its potential for solving multi-task optimization problems.
Similar content being viewed by others
Notes
The friedman test is implemented by the KEEL Software Tool available at https://sci2s.ugr.es/keel/.
References
Pearce M, Branke J (2018) Continuous multi-task bayesian optimisation with corre- lation. Eur J Oper Res 270(3):1074–1085
Ong YS, Gupta A (2016) Evolutionary multitasking: a computer science view of cognitive multitasking. Cognitive Computation 8:125–142
Tan KC, Feng L, Jiang M (2021) Evolutionary transfer optimization-a new fron- tier in evolutionary computation research. IEEE Comput Intell Mag 16(1):22–33
Gupta A, Ong YS, Feng L (2015) Multifactorial evolution: toward evolutionary multitasking. IEEE Trans Evol Comput 20(3):343–357
Wang D, Liu K, Feng L, Dai P, Wu W, Guo S (2021) Evolutionary multitasking for cross-domain task optimization via vehicular edge computing. In: 2021 IEEE Global Communications Conference (GLOBECOM), pp. 1–6
Tam NT, Dat VT, Lan PN, Binh HTT, Swami A et al (2021) Multifacto- rial evolutionary optimization to maximize lifetime of wireless sensor network. Information Sciences 576:355–373
Zhang F, Mei Y, Nguyen S, Zhang M, Tan KC (2021) Surrogate-assisted evolu- tionary multitask genetic programming for dynamic exible job shop scheduling. IEEE Trans Evol Comput 25(4):651–665
Feng L, Huang Y, Zhou L, Zhong J, Gupta A, Tang K, Tan KC (2020) Explicit evolutionary multitasking for combinatorial optimization: A case study on capaci- tated vehicle routing problem. IEEE trans cybern 51(6):3143–3156
Yang C, Ding J, Jin Y, Wang C, Chai T (2018) Multitasking multiobjective evolutionary operational indices optimization of beneficiation processes. IEEE Trans Autom Sci Eng 16(3):1046–1057
Chopra N, Ansari MM (2022) Golden jackal optimization: A novel nature-inspired optimizer for engineering applications. Expert Systems with Applications 198:116924
Abualigah L, Abd Elaziz M, Sumari P, Geem ZW, Gandomi AH (2022) Rep- tile search algorithm (rsa): A nature-inspired meta-heuristic optimizer. Expert Systems with Applications 191:116158
Seyyedabbasi A, Kiani F (2022) Sand cat swarm optimization: A nature-inspired algorithm to solve global optimization problems. Engineering with Computers 1–25
Črepinšek M, Liu SH, Mernik M, Ravber M (2019) Long term memory assistance for evolutionary algorithms. Mathematics 7(11):1129
Lou Y, Yuen SY, Chen G (2021) Non-revisiting stochastic search revisited: Results, perspectives, and future directions. Swarm and Evolutionary Computation 61:100828
Fuchs H, Kedem ZM, Naylor BF (1980) On visible surface generation by a pri- ori tree structures. In: Proceedings of the 7th Annual Conference on Computer Graphics and Interactive Techniques, pp. 124–133
Salembier P, Garrido L (2000) Binary partition tree as an efficient representation for image processing, segmentation, and information retrieval. IEEE trans Image Process 9(4):561–576
Tøndel P, Johansen TA, Bemporad A (2003) Evaluation of piecewise affine control via binary search tree. Automatica 39(5):945–950
Yuen SY, Chow CK (2007) A non-revisiting genetic algorithm. In: 2007 IEEE Congress on Evolutionary Computation, pp. 4583–4590
Xu Q, Wang N, Wang L, Li W, Sun Q (2021) Multi-task optimization and multi- task evolutionary computation in the past five years: A brief review. Mathematics 9(8):864
Feng L, Zhou L, Gupta A, Zhong J, Zhu Z, Tan KC, Qin K (2019) Solv- ing generalized vehicle routing problem with occasional drivers via evolutionary multitasking. IEEE trans cybern 51(6):3171–3184
Zheng X, Qin AK, Gong M, Zhou D (2019) Self-regulated evolutionary multi- task optimization. IEEE Trans Evol Comput 24(1):16–28
Bali KK, Ong YS, Gupta A, Tan PS (2019) Multifactorial evolutionary algo- rithm with online transfer parameter estimation: Mfea-ii. IEEE Trans Evol Comput 24(1):69–83
Liang Z, Liang W, Wang Z, Ma X, Liu L, Zhu Z (2021) Multiobjective evolution- ary multitasking with two-stage adaptive knowledge transfer based on population distribution. IEEE Transactions on Systems, Man, and Cybernetics: Systems 52(7):4457–4469
Liang Z, Xu X, Liu L, Tu Y, Zhu Z (2021) Evolutionary many-task optimization based on multisource knowledge transfer. IEEE Trans Evol Comput 26(2):319–333
Cai Y, Peng D, Liu P, Guo JM (2021) Evolutionary multi-task optimization with hybrid knowledge transfer strategy. Information Sciences 580:874–896
Xue X, Zhang K, Tan KC, Feng L, Wang J, Chen G, Zhao X, Zhang L, Yao J (2020) Affine transformation-enhanced multifactorial optimization for heterogeneous problems. IEEE Trans Cybern 52(7):6217–6231
Feng L, Zhou W, Zhou L, Jiang S, Zhong J, Da B, Zhu Z, Wang Y (2017) An empirical study of multifactorial pso and multifactorial de. In: 2017 IEEE Congress on Evolutionary Computation (CEC), pp. 921–928
Wang R, Hao K, Huang B, Zhu X (2023) Adaptive niching particle swarm opti- mization with local search for multimodal optimization. Applied Soft Computing 133:109923
Tan Z, Li K (2021) Differential evolution with mixed mutation strategy based on deep reinforcement learning. Applied Soft Computing 111:107678
Tan Z, Tang Y, Li K, Huang H, Luo S (2022) Differential evolution with hybrid parameters and mutation strategies based on reinforcement learning. Swarm and Evolutionary Computation 75:101194
Tanabe R, Fukunaga A (2013) Success-history based parameter adaptation for dif- ferential evolution. In: 2013 IEEE Congress on Evolutionary Computation, pp. 71–78
Li Y, Gong W, Li S (2023) Multitasking optimization via an adaptive solver multitasking evolutionary framework. Information Sciences 630:688–712
Tang Z, Gong M, Jiang F, Li H, Wu Y (2019) Multipopulation optimization for multitask optimization. In: 2019 IEEE Congress on Evolutionary Computation (CEC), pp. 1906–1913
Zheng X, Lei Y, Qin AK, Zhou D, Shi J, Gong M (2019) Differential evolutionary multi-task optimization. In: 2019 IEEE Congress on Evolutionary Computation (CEC), pp. 1914–1921
Li Y, Gong W, Li S (2023) Evolutionary competitive multitasking optimization via improved adaptive differential evolution. Expert Systems with Applications 119550
Glover F, Laguna M (1998) Tabu search. In: Handbook of Combinatorial Optimiza- tion, pp. 2093–2229
Kratica J (1999) Improving performances of the genetic algorithm by caching. Com- puters and artificial intelligence 18(3):271–283
Ronald S (1998) Duplicate genotypes in a genetic algorithm. In: 1998 IEEE Inter- national Conference on Evolutionary Computation Proceedings, pp. 793–798
Črepinšek M, Liu SH, Mernik M, Ravber M (2022) The trap of sisyphean work in differential evolution and how to avoid it. In: Differential Evolution: From Theory to Practice, pp. 137–174
Črepinšek M, Mernik M, Liu SH (2011) Analysis of exploration and exploitation in evolutionary algorithms by ancestry trees. International Journal of Innovative Computing and Applications 3(1):11–19
Su Y, Guo N, Tian Y, Zhang X (2020) A non-revisiting genetic algorithm based on a novel binary space partition tree. Information Sciences 512:661–674
Zhao J, Fu Y, Mei J (2015) An improved qpso algorithm based on entire search history. In: 2015 14th International Symposium on Distributed Computing and Applications for Business Engineering and Science (DCABES), pp. 74–77
Veek N, Mernik M, Filipi B, Repinek M (2016) Parameter tuning with chess rating system (crs-tuning) for meta-heuristic algorithms. Information Sciences 372(C):446–469
Cheng J (2010) Cuda by example: an introduction to general-purpose gpu program- ming. Scalable Computing: Practice and Experience 11(4):401
Guide D (2013) Cuda c programming guide. NVIDIA, July 29, 31 (2013)
Li G, Zhang Q, Gao W (2018) Multipopulation evolution framework for multifacto- rial optimization. In: Proceedings of the Genetic and Evolutionary Computation Conference Companion, pp. 215–216
Da B, Ong YS, Feng L, Qin AK, Gupta A, Zhu Z, Ting CK, Tang K, Yao X (2017) Evolutionary multitasking for single-objective continuous optimization: Benchmark problems, performance metric, and baseline results. arXiv:1706.03470
Wang C, Liu J, Wu K, Wu Z (2021) Solving multitask optimization problems with adaptive knowledge transfer via anomaly detection. IEEE Trans Evol Comput 26(2):304–318
Zhou L, Feng L, Tan KC, Zhong J, Zhu Z, Liu K, Chen C (2020) Toward adaptive knowledge transfer in multifactorial evolutionary computation. IEEE trans cybern 51(5):2563–2576
Li G, Zhang Q, Wang Z (2022) Evolutionary competitive multitasking optimization. IEEE Trans Evol Comput 26(2):278–289
Derrac J, García S, Molina D, Herrera F (2011) A practical tutorial on the use of nonparametric statistical tests as a methodology for comparing evolutionary and swarm intelligence algorithms. Swarm and Evolutionary Computation 1(1):3–18
Acknowledgements
This study received support from the Central Government Guided Local Science and Technology Development Fund Project (1653137155953), the General Project of the Liaoning Provincial Department of Education (LJKMZ20220613), the Ningxia Natural Science Foundation Project (2023AAC03361), and the 111 Project (B16009).
Author information
Authors and Affiliations
Contributions
Yufei Yang: Methodology, Software, Validation, Formal analysis, Data curation, Writing-Original Draft, Visualization, Investigation. Changsheng Zhang: Methodology, Software, Validation, Formal analysis, Data curation, Writing Reviewing and Editing, Visualization. Bin Zhang: Conceptualization, Investigation, Resources, Supervision, Project administration, Funding acquisition.
Corresponding author
Ethics declarations
Competing interests
All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix A Revisits in MTEAs and STEAs
Appendix A Revisits in MTEAs and STEAs
The paper investigates the performance of two algorithms, GA and MFEA-II, on the CEC2017 multi-task benchmark test set. The study is conducted under identical experimental conditions as presented in Section 4 to illustrate the difference between revisits in STEAs and MTEAs. The convergence curves of GA and MFEA-II for problems 1 to 9 are presented in Fig. 10, Fig. 11, and Fig. 12.
MFEA-II outperforms GA in terms of producing better final results due to knowledge transfer and consistently converging earlier than GA. However, the study finds that MFEA-II explores specific local regions faster, resulting in repeated explorations of previously searched regions as the iteration progresses. This phenomenon wastes computational resources despite the aim to optimize results. The study shows that this phenomenon occurs more frequently and earlier in MTOPs than in single-task optimization (STO) due to the positive knowledge transfer effect.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Yang, Y., Zhang, C. & Zhang, B. A non-revisiting framework for evolutionary multi-task optimization. Appl Intell 53, 25931–25953 (2023). https://doi.org/10.1007/s10489-023-04918-5
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-023-04918-5