An Evolutionary Computation Based Model for Testing Transfer Learning Strategies
Pages 1380 - 1389
Abstract
To study how Transfer Learning (TL) works and what are effective strategies for transfer learning, we propose to model the TL process using Evolutionary Computation. EC provides a clear model for a problem as searching through a set of potential solutions. We are able to more easily control and measure problem difficulty, problem similarity, and methods of information transfer and relate these to success. As a proof of concept, we will use a static source problem and three fixed target problems with simple known relationships (see Section III). We compare the effectiveness of several ways to transfer knowledge learned from solving one problem to solving the new problems in the context of the relationship between the problems. This we hope will demonstrate that using our EC model is a fruitful way to investigate TL. The results show there is an improvement for using some sampled methods representing the "learned knowledge" of the source problem S. Also, the results show that the diversity of the transferred population has some positive effect on finding the optimal solution depending on the relationship between source and target problems.
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]
L. Torrey and J. Shavlik, “Transfer learning,” in Handbook of research on machine learning applications and trends: algorithms, methods, and techniques. IGI Global, 2010, pp. 242–264.
[3]
A. E. Eiben and J. E. Smith, Introduction to Evolutionary Computing, 2nd ed. Spinger, 2015.
[4]
Q. Sun, Y. Liu, T.-S. Chua, and B. Schiele, “Meta-transfer learning for few-shot learning,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2019, pp. 403–412.
[5]
Y. Wei, Y. Zheng, and Q. Yang, “Transfer knowledge between cities,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, pp. 1905–1914.
[6]
M. Long, J. Wang, G. Ding, D. Shen, and Q. Yang, “Transfer learning with graph co-regularization,” IEEE Transactions on Knowledge and Data Engineering, vol. 26, no. 7, pp. 1805–1818, 2013.
[7]
S. K. Smit and A. E. Eiben, “Using entropy for parameter analysis of evolutionary algorithms,” in Experimental Methods for the Analysis of Optimization Algorithms. Springer, 2010, pp. 287–310.
[8]
M. Vargas, G. Fuertes, M. Alfaro, G. Gatica, S. Gutierrez, and M. Peralta, “The effect of entropy on the performance of modified genetic algorithm using earthquake and wind time series,” Complexity, vol. 2018, 2018.
[9]
D. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning. Reading, MA: Addison-Wesley Publishing, Co., 1989.
[10]
C. Darwin, On the Origin of Species: A Facsimile of the First Edition. Cambridge, MA, USA: Harvard University Press, 2001.
[11]
W. Banzhaf, R. Keller, and F. Francone, Genetic Programming: An Introduction. Morgan Kaufmann, 1998.
[12]
M. Mitchell, An introduction to genetic algorithms. MIT press, 1998.
[13]
K. Weiss, T. M. Khoshgoftaar, and D. Wang, “A survey of transfer learning,” Journal of Big data, vol. 3, no. 1, pp. 1–40, 2016.
[14]
B. Koc¸er and A. Arslan, “Genetic transfer learning,” Expert Systems with Applications, vol. 37, no. 10, pp. 6997–7002, 2010.
[15]
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.
[16]
G. Ruan, L. L. Minku, S. Menzel, B. Sendhoff, and X. Yao, “When and how to transfer knowledge in dynamic multi-objective optimization,” in 2019 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE, 2019, pp. 2034–2041.
[17]
B. Muller, H. Al-Sahaf, B. Xue, and M. Zhang, “Transfer learning: a building block selection mechanism in genetic programming for symbolic regression,” in Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2019, pp. 350–351.
[18]
R. B. Heckendorn, “Embedded landscapes,” Evolutionary Computation, vol. 10, no. 4, pp. 345–376, 2002.
[19]
P. Larrañaga and J. A. Lozano, Estimation of distribution algorithms: A new tool for evolutionary computation. Springer Science & Business Media, 2001, vol. 2.
[20]
C. E. Shannon, “A mathematical theory of communication,” Bell system technical journal, vol. 27, no. 3, pp. 379–423, 1948.
Index Terms
- An Evolutionary Computation Based Model for Testing Transfer Learning Strategies
Index terms have been assigned to the content through auto-classification.
Recommendations
Transfer learning using computational intelligence
Transfer learning aims to provide a framework to utilize previously-acquired knowledge to solve new but similar problems much more quickly and effectively. In contrast to classical machine learning methods, transfer learning methods exploit the ...
Comments
Information & Contributors
Information
Published In
Jun 2021
2584 pages
Copyright © 2021.
Publisher
IEEE Press
Publication History
Published: 28 June 2021
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 25 Dec 2024