IEEE Computational Intelligence Magazine - November 2021 - 53

transformation in many-tasking problems would be enhanced
with more sophisticated techniques. In addition to gene similarity,
it would be interesting to design more effective knowledge
transfer by accounting for other information such as the
search direction and the population distribution. Additional
transfer learning techniques with machine learning can be
introduced into evolutionary multitasking optimization to
improve knowledge transfer. This work can also be extended
to many-tasking optimization, dynamic optimization, and
combinatorial optimization.
Acknowledgment
This work was supported in part by the National Natural Science
Foundation of China, under Grants 61976143, 61871272, and
61772392, the Natural Science Foundation of Guangdong Province
under Grants 2019A1515010869 and 2020A151501946,
the Guangdong Provincial Key Laboratory under Grant
2020B121201001, the Shenzhen Fundamental Research Program,
under Grant JCYJ20190808173617147, the Science Basic
Research Plan in Shaanxi Province of China under Grant
2018JM6009, the BGI-Research Shenzhen Open Funds under
Grant BGIRSZ20200002, and the Scientific Research Foundation
of Shenzhen University for Newly-recruited Teachers, under
Grant 85304/00000247.
References
[1] K. Swersky, J. Snoek, and R. P. Adams, " Multi-task Bayesian optimization, " in Proc.
Neural Inf. Process. Syst., 2013, pp. 2004-2012.
[2] Q. Yang, Y. Zhang, W. Dai, and S. J. Pan, Transfer Learning. Cambridge, U.K.: Cambridge
Univ. Press, 2020.
[3] R. E. Lenski, C. Ofria, R. T. Pennock, and C. Adami, " The evolutionary origin of
complex features, " Nature, pp. 139-144, 2003. doi: 10.1038/nature01568.
[4] W. B. Arthur and W. Polak, " The evolution of technology within a simple computer
model, " Complexity, vol. 11, no. 5, pp. 23-31, 2006. doi: 10.1002/cplx.20130.
[5] X. Zheng, A. K. Qin, M. Gong, and D. Zhou, " Self-regulated evolutionary multi-task
optimization, " IEEE Trans. Evol. Comput., vol. 24, no. 1, pp. 16-28, 2020. doi: 10.1109/
TEVC.2019.2904696.
[6] T. Back, U. Hammel, and H. P. Schwefel, " Evolutionary computation: Comments on
the history and current state, " IEEE Trans. Evol. Comput., vol. 1, no. 1, pp. 3-17, 1997.
doi: 10.1109/4235.585888.
[7] K. Deb, Multi-Objective Optimization Using Evolutionary Algorithms. New York, NY, USA:
Wiley, 2001.
[8] S. J. Pan and Q. Yang, " A survey on transfer learning, " IEEE Trans. Knowl. Data Eng.,
vol. 22, no. 10, pp. 1345-1359, 2010. doi: 10.1109/TKDE.2009.191.
[9] W. Jaskowski, K. Krawiec, and B. Wieloch, " Multitask visual learning using genetic programming, "
Evol. Comput., vol. 16, no. 4, pp. 439-459, 2008. doi: 10.1162/evco.2008.16.4.439.
[10] D. E. Moriarty and R. Miikkulainen, " Forming neural networks through efficient
and adaptive coevolution, " Evol. Comput., vol. 5, no. 4, pp. 373-399, 1997. doi: 10.1162/
evco.1997.5.4.373.
[11] A. Gupta, Y. S. Ong, and L. Feng, " Multifactorial evolution: Toward evolutionary
multitasking, " IEEE Trans. Evol. Comput., vol. 20, no. 3, pp. 343-357, 2016. doi: 10.1109/
TEVC.2015.2458037.
[12] L. Feng, Y. S. Ong, M. H. Lim, and W. H. Tsang, " Memetic search with interdomain
learning: A realization between CVRP and CARP, " IEEE Trans. Evol. Comput.,
vol. 19, no. 5, pp. 644-658, 2015. doi: 10.1109/TEVC.2014.2362558.
[13] A. Gupta, Y. S. Ong, and L. Feng, " Insights on transfer optimization: Because experience
is the best teacher, " IEEE Trans. Evol. Comput., vol. 2, no. 1, pp. 51-64, 2018. doi:
10.1109/TETCI.2017.2769104.
[14] A. Gupta, Y. S. Ong, L. Feng, and K. C. Tan, " Multiobjective multifactorial optimization
in evolutionary multitasking, " IEEE Trans. Cybern., vol. 47, no. 7, pp. 1652-1665,
2017. doi: 10.1109/TCYB.2016.2554622.
[15] A. T. W. Min, A. Gupta, Y. S. Ong, and C. K. Goh, " Multiproblem surrogates:
Transfer evolutionary multiobjective optimization of computationally expensive problems, "
IEEE Trans. Evol. Comput., vol. 23, no. 1, pp. 15-28, 2019. doi: 10.1109/TEVC
.2017.2783441.
[16] R. Sagarna and Y. S. Ong, " Concurrently searching branches in software tests generation
through multitask evolution, " in Proc. IEEE Symp. Ser. Comput. Intell., 2017, pp. 1-8.
[17] B. Liang et al., " An evolutionary multitasking algorithm for cloud computing service
composition, " in Proc. World Congr. Services, 2018, pp. 130-144.
[18] L. Zhou, L. Feng, J. Zhong, Y.-S. Ong, and E. Sha, " Evolutionary multitasking in
combinatorial search spaces: A case study in capacitated vehicle routing problem, " in Proc.
2016 IEEE Symp. Ser. Comput. Intell. (SSCI), pp. 1-8. doi: 10.1109/SSCI.2016.7850039.
[19] J. Ding, C. Yang, Y. Jin, and T. Chai, " Generalized multi-tasking for evolutionary
optimization of expensive problems, " IEEE Trans. Evol. Comput., vol. 23, no. 1,
pp. 44-58, 2019. doi: 10.1109/TEVC.2017.2785351.
[20] D. Wu and X. Tan, " Multi-tasking genetic algorithm (MTGA) for fuzzy system optimization, "
IEEE Trans. Fuzzy Syst., vol. 28, no. 6, pp. 1050-1061, 2020. doi: 10.1109/
TFUZZ.2020.2968863.
[21] J. Yin, A. Zhu, Z. Zhu, Y. Yu, and X. Ma, " Multifactorial evolutionary algorithm
enhanced with cross-task search direction, " in Proc. 2019 IEEE Congr. Evol. Comput.
(CEC), pp. 1-8. doi: 10.1109/CEC.2019.8789959.
[22] K. K. Bali, A. Gupta, F. Liang, Y. S. Ong, and P. S. Tan, " Linearized domain adaptation
in evolutionary multitasking, " in Proc. IEEE Congr. Evol. Comput., 2017, pp. 1295-1302.
[23] L. Feng, L. Zhou, J. Zhong, A. Gupta, Y. S. Ong, K. C. Tan, and A. K. Qin, " Evolutionary
multitasking via explicit autoencoding, " IEEE Trans. Cybern., vol. 49, no. 9,
pp. 3457-3470, 2019. doi: 10.1109/TCYB.2018.2845361.
[24] Z. Liang, J. Zhang, L. Feng, and Z. Zhu, " A hybrid of genetic transform and hyperrectangle
search strategies for evolutionary multi-tasking, " Expert Syst. Appl., vol. 138,
pp. 1-18, 2019. doi: 10.1016/j.eswa.2019.07.015.
[25] B. Da, A. Gupta, and Y. S. Ong, " Curbing negative influences online for seamless
transfer evolutionary optimization, " IEEE Trans. Cybern., vol. 49, no. 12, pp. 4365-4378,
2019. doi: 10.1109/TCYB.2018.2864345.
[26] J. Zhang, W. Zhou, X. Chen, W. Yao, and L. Cao, " Multisource selective transfer
framework in multiobjective optimization problems, " IEEE Trans. Evol. Comput., vol. 24,
no. 3, pp. 424-438, 2020.
[27] S. Huang, J. Zhong, and W. Yu, " Surrogate-assisted evolutionary framework with
adaptive knowledge transfer for multi-task optimization, " IEEE Trans. Emerg. Topics Comput.,
early access, Oct. 10, 2019. doi: 10.1109/TETC.2019.2945775.
[28] K. K. Bali, Y. S. Ong, A. Gupta, and P. Tan, " Multifactorial evolutionary algorithm
with online transfer parameter estimation: MFEA-II, " IEEE Trans. Evol. Comput., vol. 24,
no. 1, pp. 69-83, 2020. doi: 10.1109/TEVC.2019.2906927.
[29] A. Gupta and Y. S. Ong, " Multitask knowledge transfer across problems, " in Memetic Computation,
Adaptation, Learning, and Optimization. New York: Springer-Verlag, 2019, pp. 83-92.
[30] S. Kullback and R. A. Leibler, " On information and sufficiency, " Ann. Math. Statist.,
vol. 22, no. 1, pp. 79-86, 1951. doi: 10.1214/aoms/1177729694.
[31] H. R. Tizhoosh, " Opposition-based learning: A new scheme for machine intelligence, "
in Proc. Int. Conf. Comput. Intell. Model., Control Automat., 2005, pp. 695-701.
[32] H. Wang, Z. Wu, S. Rahnamayan, Y. Liu, and M. Ventresca, " Enhancing particle
swarm optimization using generalized opposition-based learning, " Inf. Sci., vol. 181, no.
20, p. 4699-4714, 2011. doi: 10.1016/j.ins.2011.03.016.
[33] X. Ma, Q. Chen, Y. Yu, Y. Sun, and Z. Zhu, " A two-level transfer learning algorithm
for evolutionary multitasking, " Front. Neurosci, vol. 13, p. 1408, 2020.
[34] R. Lim, A. Gupta, Y. S. Ong, L. Feng, and A. N. Zhang, " Non-linear domain adaptation
in transfer evolutionary optimization, " Cogn. Comput., vol. 13, pp. 290-307, 2021.
doi: 10.1007/s12559-020-09777-7.
[35] Y. W. Wen and C. K. Ting, " Parting ways and reallocating resources in evolutionary
multitasking, " in Proc. IEEE Congr. Evol. Comput., 2017, pp. 2404-2411.
[36] X. Zheng, A. K. Qin, M. Gong, and D. Zhou, " Self-regulated evolutionary multi-task
optimization, " IEEE Trans. Evol. Comput., vol. 24, no. 1, pp. 16-28, 2020. doi: 10.1109/
TEVC.2019.2904696.
[37] C. Yang, J. Ding, Y. Jin, and T. Chai, " Offline data-driven multiobjective optimization:
Knowledge transfer between surrogates and generation of final solutions, " IEEE
Trans. Evol. Comput., vol. 24, no. 3, pp. 409-423, 2020.
[38] H. Wang, L. Feng, Y. Jin, and J. Doherty, " Surrogate-assisted evolutionary multitasking
for expensive minimax optimization in multiple scenarios, " IEEE Comput. Intell.
Mag., vol. 16, no. 1, pp. 34-48, 2021. doi: 10.1109/MCI.2020.3039067.
[39] R. T. Liaw and C. K. Ting, " Evolution of biocoenosis through symbiosis with fitness
approximation for many-tasking optimization, " Memetic Comput., vol. 12, no. 4, pp. 399-
417, 2020. doi: 10.1007/s12293-020-00317-2.
[40] J. Tang, Y. Chen, Z. Deng, Y. Xiang, and C. P. Joy, " A group-based approach to
improve multifactorial evolutionary algorithm, " in Proc. Int. Joint Conf. Artif. Intell., 2018,
pp. 3870-3876.
[41] Y. Yu, A. Zhu, Z. Zhu, Q. Lin, J. Yin, and X. Ma, " Multifactorial differential evolution
with opposition-based learning for multi-tasking optimization, " in Proc. IEEE Congr.
Evol. Comput., 2019, pp. 1898-1905.
[42] L. Feng et al., " An empirical study of multifactorial PSO and multifactorial DE, " in
Proc. IEEE Congr. Evol. Comput., 2017, pp. 921-928.
[43] J. Kennedy and R. Eberhart, " Particle swarm optimization, " in Proc. IEEE Int. Conf.
Neural Netw., 1995, pp. 1942-1948.
[44] K. Deb and H. Beyer, " Self-adaptive genetic algorithms with simulated binary crossover, "
Evol. Comput., vol. 9, no. 2, pp. 197-221, 2001. doi: 10.1162/106365601750190406.
[45] S. Rahnamayan, H. Tizhoosh, and M. Salama, " Opposition versus randomness in soft
computing techniques, " Appl. Soft Comput., vol. 8, no. 2, pp. 906-918, 2008. doi: 10.1016/
j.asoc.2007.07.010.
[46] B. Da et al., " Evolutionary multitasking for single-objective continuous optimization:
Benchmark problems, performance metric, and baseline results, " Nanyang Technological
University, 2017.
[47] K. Deb, S. Agrawal, A. Pratap, and T. Meyarivan, " A fast and elitist multiobjective
genetic algorithm: NSGA-II, " IEEE Trans. Evol. Comput., vol. 6, no. 2, pp. 182-197,
2002. doi: 10.1109/4235.996017.
NOVEMBER 2021 | IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE 53
IEEE Computational Intelligence Magazine - November 2021

Table of Contents for the Digital Edition of IEEE Computational Intelligence Magazine - November 2021
