Non-linear Domain Adaptation in Transfer Evolutionary Optimization

Abstract

The cognitive ability to learn with experience is a hallmark of intelligent systems. The emerging transfer optimization paradigm pursues such human-like problem-solving prowess by leveraging useful information from various source tasks to enhance optimization efficiency on a related target task. The occurrence of harmful negative transfer is a key concern in this setting, paving the way for recent probabilistic model-based transfer evolutionary algorithms that curb this phenomenon. However, in applications where the source and target domains, i.e., the features of their respective search spaces (e.g., dimensionality) and the distribution of good solutions in those spaces, do not match, narrow focus on curbing negative effects can lead to the conservative cancellation of knowledge transfer. Taking this cue, this paper presents a novel perspective on domain adaptation in the context of evolutionary optimization, inducing positive transfers even in scenarios of source-target domain mismatch. Our first contribution is to establish a probabilistic formulation of domain adaptation, by which source and/or target tasks can be mapped to a common solution representation space in which their discrepancy is reduced. Secondly, a domain adaptive transfer evolutionary algorithm is proposed, supporting both offline construction and online data-driven learning of non-linear mapping functions. The performance of the algorithm is experimentally verified, demonstrating superior convergence rate in comparison to state-of-the-art baselines on synthetic benchmarks and a practical case study in multi-location inventory planning. Our results thus shed light on a new research direction for optimization algorithms that improve their efficacy by learning from heterogeneous experiential priors.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Source data comes from the multimodal Griewank function

Fig. 7
Fig. 8

References

  1. 1.

    Gupta A, Ong YS. Back to the roots: Multi-x Evolutionary Computation. Cogn Comput. 2019;11(1):1–17.

    Article  Google Scholar 

  2. 2.

    Mahale RA, Chavan SD. A survey: Evolutionary and Swarm Based Bio-Inspired Optimization Algorithms. International Journal of Scientific and Research Publications. 2012;2(12):1–6.

    Article  Google Scholar 

  3. 3.

    Xu W, Xu JX, He D, Tan KC. An Evolutionary Constraint-Handling Technique for Parametric Optimization of a Cancer Immunotherapy Model. IEEE Trans Emerg Topics Comput Intell. 2019;3(2):151–62.

    Article  Google Scholar 

  4. 4.

    Jin Y, Wang H, Chugh T, Guo D, Miettinen K. Data-driven Evolutionary Optimization: An Overview and case studies. IEEE Trans Evol Comput. 2019;23(3):442–58.

    Article  Google Scholar 

  5. 5.

    Eremeev AV, Kovalenko YV. A Memetic Algorithm with Optimal Recombination for the Asymmetric Travelling Salesman Problem. Memetic Computing. 2020;12(1):23–36.

    Article  Google Scholar 

  6. 6.

    Gupta A, Ong YS. Memetic computation: The Mainspring of Knowledge Transfer in a Data-driven Optimization Era. Vol 21. Springer; 2018.

  7. 7.

    Gupta A, Ong YS, Feng L. Insights on Transfer Optimization: Because Experience is the Best Teacher. IEEE Trans Emerg Topics Comput Intell. 2018;2(1):51–64.

    Article  Google Scholar 

  8. 8.

    Kaedi M, Ghasem-Aghaee N. Biasing Bayesian Optimization Algorithm using Case Based Reasoning. Knowl Based Syst. 2011;24(8):1245–53.

    Article  Google Scholar 

  9. 9.

    Pelikan M, Hauschild MW, Lanzi PL. Transfer Learning, Soft Distance-Based Bias, and the Hierarchical boa. In Proceedings of the International Conference on Parallel Problem Solving in Nature 2012 Sep 1 (pp. 173–183). ACM.

  10. 10.

    Feng L, Ong YS, Tan AH, Tsang IW. Memes as Building Blocks: A Case Study on Evolutionary Optimization+ Transfer Learning for Routing Problems. Memet Comput. 2015;7(3):159–80.

    Article  Google Scholar 

  11. 11.

    Feng L, Ong YS, Lim MH, Tsang IW. Memetic Search with Inter-domain Learning: A realization between CVRP and CARP. IEEE Trans Evol Comput. 2015;19(5):644–58.

    Article  Google Scholar 

  12. 12.

    Iqbal M, Browne WN, Zhang M. Extracting and using Building Blocks of Knowledge in Learning Classifier Systems. In Proceedings of the Genetetic and Evolutionary Computation Conference 2012 Jul 7 (pp. 863–870). ACM. 

  13. 13.

    Iqbal M, Browne WN, Zhang M. Reusing Building Blocks of Extracted Knowledge to Solve Complex, Large-scale Boolean Problems. IEEE Trans Evol Comput. 2014;18(4):465–580.

    Article  Google Scholar 

  14. 14.

    Gupta A, Ong YS, Feng L. Multifactorial Evolution: Toward Evolutionary Multitasking. IEEE Trans Evol Comput. 2016;20(3):343–57.

    Article  Google Scholar 

  15. 15.

    Ong YS, Gupta A. Evolutionary Multitasking: A Computer Science View of Cognitive Multitasking. Cogn Comput. 2016;8(2):125–42.

    Article  Google Scholar 

  16. 16.

    Liaw RT, Ting CK. Evolutionary Manytasking Optimization Based on Symbiosis in Biocoenosis. In Proceedings of the AAAI Conference on Artificial Intelligence 2019 Jan 27 (pp. 4295–4303). ACM.

  17. 17.

    Tang J, Chen Y, Deng Z, Xiang Y, Joy CP. A group-based approach to improve multifactorial evolutionary algorithm. In the International Joint Conferences on Artificial Intelligence IJCAI 2018 Jul 13 (pp. 3870–3876). ACM.

  18. 18.

    Zheng X, Qin AK, Gong M, Zhou D. Self-regulated Evolutionary Multi-task Optimization. IEEE Trans Evol Comput. 2020;24(1):16–28.

    Article  Google Scholar 

  19. 19.

    Min ATW, Ong YS, Gupta A, Goh CK. Multiproblem Surrogates: Transfer Evolutionary Multiobjective Optimization of Computationally Expensive Problems. IEEE Trans Evol Comput. 2019;23(1):15–28.

    Article  Google Scholar 

  20. 20.

    Yang C, Ding J, Jin Y, Wang C, Chai T. Multitasking Multiobjective Evolutionary Operational Indices Optimization of Beneficiation Processes. IEEE Trans Autom Sci Eng. 2019;16(3):1046–57.

    Article  Google Scholar 

  21. 21.

    Ardeh MA, Mei Y, Zhang M. A Novel Genetic Programming Algorithm with Knowledge Transfer for Uncertain Capacitated Arc Routing Problem. In Pacific Rim International Conference on Artificial Intelligence 2019 Aug 26 (pp. 196–200). Springer.

  22. 22.

    Moshaiov A, Tal A. Family Bootstrapping: A Genetic Transfer Learning Approach for Onsetting The Evolution for a Set of Related Robotic Tasks. In IEEE Congress on Evolutionary Computation 2014 July 6 (pp. 2801–2808). IEEE.

  23. 23.

    Sagarna R, Ong YS. Concurrently Searching Branches in Software Tests Generation Through Multitask Evolution. In IEEE Symposium Series on Computational Intelligence (SSCI) 2016 Dec 2016 (pp. 1–8). IEEE.

  24. 24.

    Louis SJ, McDonnell J. Learning with Case-injected Genetic Algorithms. IEEE Trans Evol Comput. 2004;8(4):316–28.

    Article  Google Scholar 

  25. 25.

    Smyth P, Wolpert D. Stacked density estimation. In Advances in Neural Information Processing Systems (NIPS) 1998 (pp. 668–674). ACM.

  26. 26.

    Da B, Gupta A, Ong YS. Curbing Negative Influences Online for Seamless Transfer Evolutionary Optimization. IEEE Trans Cybern. 2018;49(12):4365–78.

    Article  Google Scholar 

  27. 27.

    Zhou L, Feng L, Zhong J, Zhu Z, Da B, Wu. A Study of Similarity Measure Between Tasks for Multifactorial Evolutionary Algorithm. In Proceedings of the GECCO Companion 2018 Jul 15 (pp. 229–230). ACM.

  28. 28.

    Feng L, Ong YS, Jiang S, Gupta A. Autoencoding Evolutionary Search with Learning Across Heterogeneous Problems. IEEE Trans Evol Comput. 2017;21(5):760–72.

    Article  Google Scholar 

  29. 29.

    Bali KK, Gupta A, Feng L, Ong YS, Tan PS. Linearized Domain Adaptation in Evolutionary Multitasking. In IEEE Congress on Evolutionary Computation 2017 Jun 5 (pp. 1295–1302). IEEE.

  30. 30.

    Feng L, Zhou L, Zhong J, Gupta A, Ong YS, Tan KC, et al. Evolutionary Multitasking via Explicit Autoencoding. IEEE Trans Cybern. 2019;49(9):3457–70.

    Article  Google Scholar 

  31. 31.

    Pan SJ, Yang Q. A Survey on Transfer Learning. IEEE Trans Knowl Data Eng. 2010;22(10):1345–59.

    Article  Google Scholar 

  32. 32.

    Shakeri M, Gupta A, Ong YS, Xu C, Zhang AN. Coping with Big Data in Transfer Optimization. In IEEE International Conference on Big Data 2019 Dec 9 (pp. 3925–3932). IEEE.

  33. 33.

    Kodirov E, Xiang T, Gong S. Semantic Autoencoder for Zero-shot Learning. In IEEE Conference on Computer Vision and Pattern Recognition 2017 Jul 21 (pp. 3174–3183). IEEE.

  34. 34.

    Deng WY, Lendasse A, Ong YS, Tsang IW, Chen L, Zheng QH. Domain Adaption via Feature Selection on Explicit Feature Map. IEEE Trans Neural Netw Learn Syst. 2019;30(4):1180–90.

    MathSciNet  Article  Google Scholar 

  35. 35.

    Sun S, Shi H, Wu Y. A Survey of Multi-source Domain Adaptation. Information Fusion. 2015;24:84–92.

    Article  Google Scholar 

  36. 36.

    Krejca MS, Witt C. Theory of Estimation-of-Distribution Algorithms. Theory of Evolutionary Computation. Cham, Switzerland: Springer; 2020. (pp. 405–442).

  37. 37.

    Zhang Q, Muhlenbein H. On the Convergence of a Class of Estimation of Distribution Algorithms. IEEE Trans Evol Comput. 2004;8(2):127–36.

    Article  Google Scholar 

  38. 38.

    Baluja S, Davies S. Fast Probabilistic Modeling for Combinatorial Optimization. In Proceedings of the AAAI Conference on Artificial Intelligence 1998 Jul 26 (pp. 469–476). ACM.

  39. 39.

    Liang NY, Huang GB, Saratchandran P, Sundararajan N. A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks. IEEE Trans Neural Netw. 2006;17(6):1411–23.

    Article  Google Scholar 

  40. 40.

    Hendeby G, Gustafsson F. On Nonlinear Transformations of Gaussian Distributions. Technical Report from Automatic Control, Linkoping University, Sweden, 2007.

  41. 41.

    Feng L, Gupta A, Ong YS. Compressed Representation for Higher-level Meme Space Evolution: A Case Study on Big Knapsack Problems. Memet Comput. 2019;11(1):3–17.

    Article  Google Scholar 

  42. 42.

    Dantzig GB. Discrete-Variable Extremum Problems. Oper Res. 1957;5(2):266–88.

    MathSciNet  Article  Google Scholar 

  43. 43.

    Michalewicz Z, Arabas J. Genetic Algorithms for the 0/1 Knapsack Problem. In Proceedings of the International Symposium on Methodologies for Intelligent Systems 1994 Oct 16 (pp. 134–143). Springer.

  44. 44.

    Mühlenbein H. The Equation for Response to Selection and Its Use for Prediction. Evol Comput. 1997;5(3):303–46.

    Article  Google Scholar 

  45. 45.

    Wierstra D, Schaul T, Glasmachers T, Sun Y, Peters J, Schmidhuber J. Natural Evolution Strategies. The Journal of Machine Learning Research. 2014;15(1):949–80.

    MathSciNet  MATH  Google Scholar 

  46. 46.

    Locatelli M. A Note on the Griewank Test Function. J Glob Optim. 2003;25(2):169–74.

    MathSciNet  Article  Google Scholar 

  47. 47.

    Gomes WJ, Beck AT, Lopez RH, Miguel LF. A Probabilistic Metric for Comparing Metaheuristic Optimization Algorithms. Struct Saf. 2018;70:59–70.

    Article  Google Scholar 

  48. 48.

    Chartniyom S, Lee MK, Luong L, Marian R. Multi-location Inventory System with Lateral Transshipments and Emergency Orders. In IEEE International Conference on Industrial Engineering and Engineering Management 2007 Dec 2 (pp. 1594–1598). IEEE.

  49. 49.

    Min ATW, Gupta A, Ong YS. Generalizing Transfer Bayesian Optimization to Source-Target Heterogeneity. IEEE Transactions on Automation Science and Engineering. 2020. In Press.

Download references

Funding

This work was funded by the Agency for Science, Technology and Research (A*STAR) of Singapore, under the Singapore Institute of Manufacturing Technology-Nayang Technological University Collaborative Research Programme in Complex Systems. This work was also supported in part by the A*STAR Cyber-Physical Production System (CPPS) – Towards Contextual and Intelligent Response Research Program, under the RIE2020 IAF-PP Grant A19C1a0018. Yew-Soon Ong acknowledges the support by Singtel Cognitive and Artificial Intelligence Lab for Enterprises (SCALE@NTU), which is a collaboration between Singapore Telecommunications Limited (Singtel) and Nanyang Technological University (NTU) that is funded by the Singapore Government through the Industry Alignment Fund ‐ Industry Collaboration Projects Grant.

Author information

Affiliations

Authors

Corresponding author

Correspondence to Yew-Soon Ong.

Ethics declarations

Conflict of Interest

The authors declare that they have no conflict of interest.

Ethical Approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Lim, R., Gupta, A., Ong, YS. et al. Non-linear Domain Adaptation in Transfer Evolutionary Optimization. Cogn Comput (2021). https://doi.org/10.1007/s12559-020-09777-7

Download citation

Keywords

  • Domain adaptation
  • Solution representation learning
  • Transfer evolutionary optimization
  • Memetic computation