A sequential learnable evolutionary algorithm with a novel knowledge base generation method

Yang LOU; Shiu Yin YUEN

doi:10.1007/978-3-319-68759-9_5

A sequential learnable evolutionary algorithm with a novel knowledge base generation method

Yang LOU^*, Shiu Yin YUEN

^*Corresponding author for this work

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

1 Citation (Scopus)

Abstract

Sequential learnable evolutionary algorithm (SLEA) provides an algorithm selection framework for solving the black box continuous design optimization problems. An algorithm pool consists of set of established algorithms. A knowledge base is trained offline. SLEA uses the algorithm-problem features to select the best algorithm from the algorithm pool. Given a problem, the default algorithm is run for the initial round. After that, an algorithm-problem feature is collected and used to map to the most similar problem in the knowledge base. Then the best algorithm for solving the problem is used in the second round. This process iterates until n rounds have been made. It is revealed that the algorithm-problem feature is a good problem identifier, thus SLEA performs well on the known problems that have been encountered. However, the performance on those unknown problems is limited if the knowledge base is biased. In this paper, we propose a modified SLEA, which performs the training process using a novel method. A relatively unbiased knowledge base is formed. Experimental results show that the modified SLEA maintains the performance of SLEA on solving the CEC 2013 test suite, while it performs better than SLEA on solving a set of randomly generated max-set of Gaussian test problems.

Original language	English
Title of host publication	Simulated Evolution and Learning : 11th International Conference, SEAL 2017, Proceedings
Editors	Yuhui SHI, Kay Chen TAN, Mengjie ZHANG, Ke TANG, Xiaodong LI, Qingfu ZHANG, Ying TAN, Martin MIDDENDORF, Yaochu JIN
Publisher	Springer-Verlag GmbH and Co. KG
Pages	51-61
Number of pages	11
Volume	10593
ISBN (Print)	9783319687582
DOIs	https://doi.org/10.1007/978-3-319-68759-9_5
Publication status	Published - 2017
Externally published	Yes
Event	11th International Conference on Simulated Evolution and Learning, SEAL 2017 - Shenzhen, China Duration: 10 Nov 2017 → 13 Nov 2017

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	10593
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	11th International Conference on Simulated Evolution and Learning, SEAL 2017
Country/Territory	China
City	Shenzhen
Period	10/11/17 → 13/11/17

Bibliographical note

Funding Information:
Acknowledgement. The work described in this paper was supported by a grant from the Research Grants Council of the Hong Kong Special Administrative Region, China [Project No. CityU 125313]. Yang Lou acknowledge the Institutional Postgraduate Studentship and the Institutional Research Tuition Grant from City University of Hong Kong.

Publisher Copyright:
© Springer International Publishing AG 2017.

Keywords

Algorithm selection
Algorithm-problem feature
Black box design optimization problem
Evolutionary algorithm

Access to Document

10.1007/978-3-319-68759-9_5

Cite this

LOU, Y., & YUEN, S. Y. (2017). A sequential learnable evolutionary algorithm with a novel knowledge base generation method. In Y. SHI, K. C. TAN, M. ZHANG, K. TANG, X. LI, Q. ZHANG, Y. TAN, M. MIDDENDORF, & Y. JIN (Eds.), Simulated Evolution and Learning : 11th International Conference, SEAL 2017, Proceedings (Vol. 10593, pp. 51-61). (Lecture Notes in Computer Science; Vol. 10593). Springer-Verlag GmbH and Co. KG. https://doi.org/10.1007/978-3-319-68759-9_5

LOU, Yang ; YUEN, Shiu Yin. / A sequential learnable evolutionary algorithm with a novel knowledge base generation method. Simulated Evolution and Learning : 11th International Conference, SEAL 2017, Proceedings. editor / Yuhui SHI ; Kay Chen TAN ; Mengjie ZHANG ; Ke TANG ; Xiaodong LI ; Qingfu ZHANG ; Ying TAN ; Martin MIDDENDORF ; Yaochu JIN. Vol. 10593 Springer-Verlag GmbH and Co. KG, 2017. pp. 51-61 (Lecture Notes in Computer Science).

@inproceedings{2c5f806cff75475dbfa21b485d82a1f0,

title = "A sequential learnable evolutionary algorithm with a novel knowledge base generation method",

abstract = "Sequential learnable evolutionary algorithm (SLEA) provides an algorithm selection framework for solving the black box continuous design optimization problems. An algorithm pool consists of set of established algorithms. A knowledge base is trained offline. SLEA uses the algorithm-problem features to select the best algorithm from the algorithm pool. Given a problem, the default algorithm is run for the initial round. After that, an algorithm-problem feature is collected and used to map to the most similar problem in the knowledge base. Then the best algorithm for solving the problem is used in the second round. This process iterates until n rounds have been made. It is revealed that the algorithm-problem feature is a good problem identifier, thus SLEA performs well on the known problems that have been encountered. However, the performance on those unknown problems is limited if the knowledge base is biased. In this paper, we propose a modified SLEA, which performs the training process using a novel method. A relatively unbiased knowledge base is formed. Experimental results show that the modified SLEA maintains the performance of SLEA on solving the CEC 2013 test suite, while it performs better than SLEA on solving a set of randomly generated max-set of Gaussian test problems.",

keywords = "Algorithm selection, Algorithm-problem feature, Black box design optimization problem, Evolutionary algorithm",

author = "Yang LOU and YUEN, {Shiu Yin}",

note = "Funding Information: Acknowledgement. The work described in this paper was supported by a grant from the Research Grants Council of the Hong Kong Special Administrative Region, China [Project No. CityU 125313]. Yang Lou acknowledge the Institutional Postgraduate Studentship and the Institutional Research Tuition Grant from City University of Hong Kong. Publisher Copyright: {\textcopyright} Springer International Publishing AG 2017.; 11th International Conference on Simulated Evolution and Learning, SEAL 2017 ; Conference date: 10-11-2017 Through 13-11-2017",

year = "2017",

doi = "10.1007/978-3-319-68759-9_5",

language = "English",

isbn = "9783319687582",

volume = "10593",

series = "Lecture Notes in Computer Science",

publisher = "Springer-Verlag GmbH and Co. KG",

pages = "51--61",

editor = "Yuhui SHI and TAN, {Kay Chen} and Mengjie ZHANG and Ke TANG and Xiaodong LI and Qingfu ZHANG and Ying TAN and Martin MIDDENDORF and Yaochu JIN",

booktitle = "Simulated Evolution and Learning : 11th International Conference, SEAL 2017, Proceedings",

address = "Germany",

}

LOU, Y & YUEN, SY 2017, A sequential learnable evolutionary algorithm with a novel knowledge base generation method. in Y SHI, KC TAN, M ZHANG, K TANG, X LI, Q ZHANG, Y TAN, M MIDDENDORF & Y JIN (eds), Simulated Evolution and Learning : 11th International Conference, SEAL 2017, Proceedings. vol. 10593, Lecture Notes in Computer Science, vol. 10593, Springer-Verlag GmbH and Co. KG, pp. 51-61, 11th International Conference on Simulated Evolution and Learning, SEAL 2017, Shenzhen, China, 10/11/17. https://doi.org/10.1007/978-3-319-68759-9_5

A sequential learnable evolutionary algorithm with a novel knowledge base generation method. / LOU, Yang; YUEN, Shiu Yin.

Simulated Evolution and Learning : 11th International Conference, SEAL 2017, Proceedings. ed. / Yuhui SHI; Kay Chen TAN; Mengjie ZHANG; Ke TANG; Xiaodong LI; Qingfu ZHANG; Ying TAN; Martin MIDDENDORF; Yaochu JIN. Vol. 10593 Springer-Verlag GmbH and Co. KG, 2017. p. 51-61 (Lecture Notes in Computer Science; Vol. 10593).

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

TY - GEN

T1 - A sequential learnable evolutionary algorithm with a novel knowledge base generation method

AU - LOU, Yang

AU - YUEN, Shiu Yin

N1 - Funding Information: Acknowledgement. The work described in this paper was supported by a grant from the Research Grants Council of the Hong Kong Special Administrative Region, China [Project No. CityU 125313]. Yang Lou acknowledge the Institutional Postgraduate Studentship and the Institutional Research Tuition Grant from City University of Hong Kong. Publisher Copyright: © Springer International Publishing AG 2017.

PY - 2017

Y1 - 2017

N2 - Sequential learnable evolutionary algorithm (SLEA) provides an algorithm selection framework for solving the black box continuous design optimization problems. An algorithm pool consists of set of established algorithms. A knowledge base is trained offline. SLEA uses the algorithm-problem features to select the best algorithm from the algorithm pool. Given a problem, the default algorithm is run for the initial round. After that, an algorithm-problem feature is collected and used to map to the most similar problem in the knowledge base. Then the best algorithm for solving the problem is used in the second round. This process iterates until n rounds have been made. It is revealed that the algorithm-problem feature is a good problem identifier, thus SLEA performs well on the known problems that have been encountered. However, the performance on those unknown problems is limited if the knowledge base is biased. In this paper, we propose a modified SLEA, which performs the training process using a novel method. A relatively unbiased knowledge base is formed. Experimental results show that the modified SLEA maintains the performance of SLEA on solving the CEC 2013 test suite, while it performs better than SLEA on solving a set of randomly generated max-set of Gaussian test problems.

AB - Sequential learnable evolutionary algorithm (SLEA) provides an algorithm selection framework for solving the black box continuous design optimization problems. An algorithm pool consists of set of established algorithms. A knowledge base is trained offline. SLEA uses the algorithm-problem features to select the best algorithm from the algorithm pool. Given a problem, the default algorithm is run for the initial round. After that, an algorithm-problem feature is collected and used to map to the most similar problem in the knowledge base. Then the best algorithm for solving the problem is used in the second round. This process iterates until n rounds have been made. It is revealed that the algorithm-problem feature is a good problem identifier, thus SLEA performs well on the known problems that have been encountered. However, the performance on those unknown problems is limited if the knowledge base is biased. In this paper, we propose a modified SLEA, which performs the training process using a novel method. A relatively unbiased knowledge base is formed. Experimental results show that the modified SLEA maintains the performance of SLEA on solving the CEC 2013 test suite, while it performs better than SLEA on solving a set of randomly generated max-set of Gaussian test problems.

KW - Algorithm selection

KW - Algorithm-problem feature

KW - Black box design optimization problem

KW - Evolutionary algorithm

UR - http://www.scopus.com/inward/record.url?scp=85034271500&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-68759-9_5

DO - 10.1007/978-3-319-68759-9_5

M3 - Conference paper (refereed)

AN - SCOPUS:85034271500

SN - 9783319687582

VL - 10593

T3 - Lecture Notes in Computer Science

SP - 51

EP - 61

BT - Simulated Evolution and Learning : 11th International Conference, SEAL 2017, Proceedings

A2 - SHI, Yuhui

A2 - TAN, Kay Chen

A2 - ZHANG, Mengjie

A2 - TANG, Ke

A2 - LI, Xiaodong

A2 - ZHANG, Qingfu

A2 - TAN, Ying

A2 - MIDDENDORF, Martin

A2 - JIN, Yaochu

PB - Springer-Verlag GmbH and Co. KG

T2 - 11th International Conference on Simulated Evolution and Learning, SEAL 2017

Y2 - 10 November 2017 through 13 November 2017

ER -

LOU Y, YUEN SY. A sequential learnable evolutionary algorithm with a novel knowledge base generation method. In SHI Y, TAN KC, ZHANG M, TANG K, LI X, ZHANG Q, TAN Y, MIDDENDORF M, JIN Y, editors, Simulated Evolution and Learning : 11th International Conference, SEAL 2017, Proceedings. Vol. 10593. Springer-Verlag GmbH and Co. KG. 2017. p. 51-61. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-319-68759-9_5

A sequential learnable evolutionary algorithm with a novel knowledge base generation method

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this