Efficient multiplayer battle game optimizer for numerical optimization and adversarial robust neural architecture search
This paper introduces a novel metaheuristic algorithm, known as the efficient multiplayer battle game optimizer (EMBGO), specifically designed for addressing complex numerical optimization tasks. The motivation behind this research stems from the need to rectify identified shortcomings in the origin...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | Alexandria Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1110016824014935 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206957401702400 |
|---|---|
| author | Rui Zhong Yuefeng Xu Chao Zhang Jun Yu |
| author_facet | Rui Zhong Yuefeng Xu Chao Zhang Jun Yu |
| author_sort | Rui Zhong |
| collection | DOAJ |
| description | This paper introduces a novel metaheuristic algorithm, known as the efficient multiplayer battle game optimizer (EMBGO), specifically designed for addressing complex numerical optimization tasks. The motivation behind this research stems from the need to rectify identified shortcomings in the original MBGO, particularly in search operators during the movement phase, as revealed through ablation experiments. EMBGO mitigates these limitations by integrating the movement and battle phases to simplify the original optimization framework and improve search efficiency. Besides, two efficient search operators: differential mutation and Lévy flight are introduced to increase the diversity of the population. To evaluate the performance of EMBGO comprehensively and fairly, numerical experiments are conducted on benchmark functions such as CEC2017, CEC2020, and CEC2022, as well as engineering problems. Twelve well-established MA approaches serve as competitor algorithms for comparison. Furthermore, we apply the proposed EMBGO to the complex adversarial robust neural architecture search (ARNAS) tasks and explore its robustness and scalability. The experimental results and statistical analyses confirm the efficiency and effectiveness of EMBGO across various optimization tasks. As a potential optimization technique, EMBGO holds promise for diverse applications in real-world problems and deep learning scenarios. The source code of EMBGO is made available in https://github.com/RuiZhong961230/EMBGO. |
| format | Article |
| id | doaj-art-80c087f63d9f4730b9e61b5d9967ea75 |
| institution | Kabale University |
| issn | 1110-0168 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Alexandria Engineering Journal |
| spelling | doaj-art-80c087f63d9f4730b9e61b5d9967ea752025-02-07T04:47:06ZengElsevierAlexandria Engineering Journal1110-01682025-02-01113150168Efficient multiplayer battle game optimizer for numerical optimization and adversarial robust neural architecture searchRui Zhong0Yuefeng Xu1Chao Zhang2Jun Yu3Information Initiative Center, Hokkaido University, Sapporo, JapanGraduate School of Science and Technology, Niigata University, Niigata, JapanSchool of Engineering, University of Toyama, Toyama, JapanInstitute of Science and Technology, Niigata University, Niigata, Japan; Corresponding author.This paper introduces a novel metaheuristic algorithm, known as the efficient multiplayer battle game optimizer (EMBGO), specifically designed for addressing complex numerical optimization tasks. The motivation behind this research stems from the need to rectify identified shortcomings in the original MBGO, particularly in search operators during the movement phase, as revealed through ablation experiments. EMBGO mitigates these limitations by integrating the movement and battle phases to simplify the original optimization framework and improve search efficiency. Besides, two efficient search operators: differential mutation and Lévy flight are introduced to increase the diversity of the population. To evaluate the performance of EMBGO comprehensively and fairly, numerical experiments are conducted on benchmark functions such as CEC2017, CEC2020, and CEC2022, as well as engineering problems. Twelve well-established MA approaches serve as competitor algorithms for comparison. Furthermore, we apply the proposed EMBGO to the complex adversarial robust neural architecture search (ARNAS) tasks and explore its robustness and scalability. The experimental results and statistical analyses confirm the efficiency and effectiveness of EMBGO across various optimization tasks. As a potential optimization technique, EMBGO holds promise for diverse applications in real-world problems and deep learning scenarios. The source code of EMBGO is made available in https://github.com/RuiZhong961230/EMBGO.http://www.sciencedirect.com/science/article/pii/S1110016824014935Metaheuristic algorithm (MA)Multiplayer battle game optimizer (MBGO)Differential mutationLévy flightAdversarial robust neural architecture search (ARNAS) |
| spellingShingle | Rui Zhong Yuefeng Xu Chao Zhang Jun Yu Efficient multiplayer battle game optimizer for numerical optimization and adversarial robust neural architecture search Alexandria Engineering Journal Metaheuristic algorithm (MA) Multiplayer battle game optimizer (MBGO) Differential mutation Lévy flight Adversarial robust neural architecture search (ARNAS) |
| title | Efficient multiplayer battle game optimizer for numerical optimization and adversarial robust neural architecture search |
| title_full | Efficient multiplayer battle game optimizer for numerical optimization and adversarial robust neural architecture search |
| title_fullStr | Efficient multiplayer battle game optimizer for numerical optimization and adversarial robust neural architecture search |
| title_full_unstemmed | Efficient multiplayer battle game optimizer for numerical optimization and adversarial robust neural architecture search |
| title_short | Efficient multiplayer battle game optimizer for numerical optimization and adversarial robust neural architecture search |
| title_sort | efficient multiplayer battle game optimizer for numerical optimization and adversarial robust neural architecture search |
| topic | Metaheuristic algorithm (MA) Multiplayer battle game optimizer (MBGO) Differential mutation Lévy flight Adversarial robust neural architecture search (ARNAS) |
| url | http://www.sciencedirect.com/science/article/pii/S1110016824014935 |
| work_keys_str_mv | AT ruizhong efficientmultiplayerbattlegameoptimizerfornumericaloptimizationandadversarialrobustneuralarchitecturesearch AT yuefengxu efficientmultiplayerbattlegameoptimizerfornumericaloptimizationandadversarialrobustneuralarchitecturesearch AT chaozhang efficientmultiplayerbattlegameoptimizerfornumericaloptimizationandadversarialrobustneuralarchitecturesearch AT junyu efficientmultiplayerbattlegameoptimizerfornumericaloptimizationandadversarialrobustneuralarchitecturesearch |