TY - JOUR
T1 - Efficient multiplayer battle game optimizer for numerical optimization and adversarial robust neural architecture search
AU - Zhong, Rui
AU - Xu, Yuefeng
AU - Zhang, Chao
AU - Yu, Jun
N1 - Publisher Copyright:
© 2024 The Authors
PY - 2025/2
Y1 - 2025/2
N2 - 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.
AB - 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.
KW - Adversarial robust neural architecture search (ARNAS)
KW - Differential mutation
KW - Lévy flight
KW - Metaheuristic algorithm (MA)
KW - Multiplayer battle game optimizer (MBGO)
UR - http://www.scopus.com/inward/record.url?scp=85209247427&partnerID=8YFLogxK
U2 - 10.1016/j.aej.2024.11.035
DO - 10.1016/j.aej.2024.11.035
M3 - 学術論文
AN - SCOPUS:85209247427
SN - 1110-0168
VL - 113
SP - 150
EP - 168
JO - Alexandria Engineering Journal
JF - Alexandria Engineering Journal
ER -