Advertisement

Multitask Knowledge Transfer Across Problems

  • Abhishek Gupta
  • Yew-Soon Ong
Chapter
Part of the Adaptation, Learning, and Optimization book series (ALO, volume 21)

Abstract

Sequential knowledge transfer dealt with the case in which we were focused on tackling a single (target) optimization problem (or task) of interest at a time, by utilizing a static knowledge base of memes learned from various past experiences on related source tasks. Thus, the transfer of memes occurred in a largely unidirectional sense, from whatever had been experienced previously, to the present. In contrast, the case of multitask knowledge transfers caters to distinct tasks of equal priority arising simultaneously. This implies that it may not be possible to await the completion of some tasks for making the acquired knowledge accessible to the others. The different optimization exercises must progress in tandem, with partially evolved memes discovered during the course of the search being spontaneously shared in a dynamic knowledge base. As a result, the transfer of knowledge takes place in all directions (in an omnidirectional sense), with the back-and-forth propagation of memes leading to more synergistic search across multiple problems at once. With this, the main goal of the current chapter is to customize the adaptive memetic transfer optimizer (AMTO), proposed in Chap. 5, for the purpose of multitasking. We label our algorithmic contribution herein as an adaptive memetic multitask optimizer (i.e., AM-MTO).

References

  1. 1.
    Gupta, A., Ong, Y. S., & Feng, L. (2016). Multifactorial evolution: Toward evolutionary multitasking. IEEE Transactions on Evolutionary Computation, 20(3), 343–357.CrossRefGoogle Scholar
  2. 2.
    Gupta, A., Ong, Y. S., & Feng, L. (2018). Insights on transfer optimization: Because experience is the best teacher. IEEE Transactions on Emerging Topics in Computational Intelligence, 2(1), 51–64.CrossRefGoogle Scholar
  3. 3.
    Gupta, A., Ong, Y. S., Feng, L., & Tan, K. C. (2017). Multiobjective multifactorial optimization in evolutionary multitasking. IEEE Transactions on Cybernetics, 47(7), 1652–1665.CrossRefGoogle Scholar
  4. 4.
    Ong, Y. S., & Gupta, A. (2016). Evolutionary multitasking: A computer science view of cognitive multitasking. Cognitive Computation, 8(2), 125–142.CrossRefGoogle Scholar
  5. 5.
    Bali, K. K., Gupta, A., Feng, L., Ong, Y. S., & Siew, T. P. (2017, June). Linearized domain adaptation in evolutionary multitasking. In 2017 IEEE Congress on Evolutionary Computation (CEC) (pp. 1295–1302). IEEE.Google Scholar
  6. 6.
    Wen, Y. W., & Ting, C. K. (2017, June). Parting ways and reallocating resources in evolutionary multitasking. In 2017 IEEE Congress on Evolutionary Computation (CEC) (pp. 2404–2411). IEEE.Google Scholar
  7. 7.
    Chandra, R., Gupta, A., Ong, Y. S., & Goh, C. K. (2017). Evolutionary multi-task learning for modular knowledge representation in neural networks. Neural Processing Letters, 1–17.Google Scholar
  8. 8.
    Tang, Z., Gong, M., & Zhang, M. (2017, June). Evolutionary multi-task learning for modular extremal learning machine. In 2017 IEEE Congress on Evolutionary Computation (CEC) (pp. 474–479). IEEE.Google Scholar
  9. 9.
    Wen, Y. W., & Ting, C. K. (2016, July). Learning ensemble of decision trees through multifactorial genetic programming. In 2016 IEEE Congress on Evolutionary Computation (CEC) (pp. 5293–5300). IEEE.Google Scholar
  10. 10.
    Cheng, M. Y., Gupta, A., Ong, Y. S., & Ni, Z. W. (2017). Coevolutionary multitasking for concurrent global optimization: With case studies in complex engineering design. Engineering Applications of Artificial Intelligence, 64, 13–24.CrossRefGoogle Scholar
  11. 11.
    Sagarna, R., & Ong, Y. S. (2016, December). Concurrently searching branches in software tests generation through multitask evolution. In 2016 IEEE Symposium Series on Computational Intelligence (SSCI) (pp. 1–8). IEEE.Google Scholar
  12. 12.
    Ding, J., Yang, C., Jin, Y., & Chai, T. (2017). Generalized multi-tasking for evolutionary optimization of expensive problems. IEEE Transactions on Evolutionary Computation. Early Access. Google Scholar
  13. 13.
    Cabi, S., Colmenarejo, S. G., Hoffman, M. W., Denil, M., Wang, Z., & Freitas, N. (2017). The intentional unintentional agent: Learning to solve many continuous control tasks simultaneously. In Conference on Robot Learning (pp. 207–216).Google Scholar
  14. 14.
    MacQueen, J. (1967, June). Some methods for classification and analysis of multivariate observations. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, 1(14), 281–297.Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of Computer Science and EngineeringNanyang Technological UniversitySingaporeSingapore
  2. 2.School of Computer Science and EngineeringNanyang Technological UniversitySingaporeSingapore

Personalised recommendations