Transfer Knowledge from Multiple Source Problems to a Target Problem in Genetic Algorithm
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 32794
Transfer Knowledge from Multiple Source Problems to a Target Problem in Genetic Algorithm

Authors: Tami Alghamdi, Terence Soule

Abstract:

To study how to transfer knowledge from multiple source problems to the target problem, we modeled the Transfer Learning (TL) process using Genetic Algorithms as the model solver. TL is the process that aims to transfer learned data from one problem to another problem. The TL process aims to help Machine Learning (ML) algorithms find a solution to the problems. The Genetic Algorithms (GA) give researchers access to information that we have about how the old problem is solved. In this paper, we have five different source problems, and we transfer the knowledge to the target problem. We studied different scenarios of the target problem. The results showed that combined knowledge from multiple source problems improves the GA performance. Also, the process of combining knowledge from several problems results in promoting diversity of the transferred population.

Keywords: Transfer Learning, Multiple Sources, Knowledge Transfer, Domain Adaptation, Source, Target.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 256

References:


[1] S. J. Pan and Q. Yang, “A survey on transfer learning,” IEEE Transactions on knowledge and data engineering, vol. 22, no. 10, pp. 1345–1359, 2009.
[2] A. E. Eiben, J. E. Smith et al., Introduction to evolutionary computing. Springer, 2003, vol. 53.
[3] M. Mitchell, An introduction to genetic algorithms. MIT press, 1998.
[4] Z. Liu and H. Wang, “Improved population prediction strategy for dynamic multi-objective optimization algorithms using transfer learning,” in 2021 IEEE Congress on Evolutionary Computation (CEC). IEEE, 2021, pp. 103–110.
[5] R. de Lima Mendes, A. H. da Silva Alves, M. de Souza Gomes, P. L. L. Bertarini, and L. R. do Amaral, “Many layer transfer learning genetic algorithm (mltlga): a new evolutionary transfer learning approach applied to pneumonia classification,” in 2021 IEEE Congress on Evolutionary Computation (CEC). IEEE, 2021, pp. 2476–2482.
[6] M. A. Ardeh, Y. Mei, and M. Zhang, “Surrogate-assisted genetic programming with diverse transfer for the uncertain capacitated arc routing problem,” in 2021 IEEE Congress on Evolutionary Computation (CEC). IEEE, 2021, pp. 628–635.
[7] L. Chen and H.-L. Liu, “Transfer learning based evolutionary algorithm for bi-level optimization problems,” in 2021 IEEE Congress on Evolutionary Computation (CEC). IEEE, 2021, pp. 1643–1647.
[8] A. Gupta and Y.-S. Ong, “Genetic transfer or population diversification? deciphering the secret ingredients of evolutionary multitask optimization,” in 2016 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE, 2016, pp. 1–7.
[9] T. Alghamdi and R. B. Heckendorn, “An evolutionary computation based model for testing transfer learning strategies,” in 2021 IEEE Congress on Evolutionary Computation (CEC). IEEE, 2021, pp. 1380–1389.