Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
80 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Efficient Multiplayer Battle Game Optimizer for Adversarial Robust Neural Architecture Search (2403.10100v1)

Published 15 Mar 2024 in cs.NE

Abstract: 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 L\'evy 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 \url{https://github.com/RuiZhong961230/EMBGO}.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (66)
  1. doi:https://doi.org/10.1007/s40747-022-00957-6.
  2. doi:https://doi.org/10.1016/j.eswa.2023.122147.
  3. doi:https://doi.org/10.1016/j.eswa.2023.122200.
  4. doi:https://doi.org/10.1016/j.knosys.2022.110206.
  5. doi:10.3390/pr9050859.
  6. doi:10.1007/s00521-023-08261-1.
  7. doi:10.3390/math10193466.
  8. doi:https://doi.org/10.1016/j.eswa.2023.122335.
  9. doi:10.1007/s11831-023-09975-0.
  10. doi:10.1007/s10462-023-10470-y.
  11. doi:10.1016/j.engappai.2023.106959.
  12. doi:10.1109/4235.585893.
  13. doi:10.3390/biomimetics8060454.
  14. arXiv:2401.00401.
  15. doi:10.1109/ICASSP.2019.8683305.
  16. arXiv:1812.09926.
  17. arXiv:1802.03268.
  18. arXiv:1906.05226.
  19. arXiv:1812.00332.
  20. arXiv:2008.06120.
  21. arXiv:2007.07197.
  22. arXiv:1911.09336.
  23. arXiv:1907.01845.
  24. arXiv:2107.02960.
  25. arXiv:2005.07564.
  26. doi:https://doi.org/10.1016/j.patcog.2022.108962.
  27. arXiv:1910.04465.
  28. arXiv:1905.13577.
  29. arXiv:1806.09055.
  30. doi:10.18653/v1/D19-1367.
  31. doi:https://doi.org/10.1016/j.patcog.2022.109193.
  32. doi:10.1145/3447582.
  33. doi:https://doi.org/10.1016/j.patcog.2023.110052.
  34. arXiv:2012.06122.
  35. arXiv:2007.08428.
  36. doi:10.1007/978-3-030-29414-4_8.
  37. doi:https://doi.org/10.1016/j.future.2020.03.055.
  38. doi:https://doi.org/10.1016/j.eswa.2023.122189.
  39. doi:10.3390/math11051273.
  40. doi:https://doi.org/10.1016/j.eswa.2023.122638.
  41. doi:10.1109/ICSMC.2011.6083925.
  42. doi:10.1109/ACCESS.2023.3295242.
  43. doi:10.1186/s13677-023-00401-1.
  44. doi:https://doi.org/10.1016/j.eswa.2022.119303.
  45. doi:https://doi.org/10.1016/j.rineng.2023.101274.
  46. doi:https://doi.org/10.1016/j.sysarc.2023.102871.
  47. T. Nguyen, A framework of optimization functions using numpy (opfunu) for optimization problems (2020). doi:10.5281/zenodo.3620960.
  48. doi:https://doi.org/10.1016/j.aej.2023.12.028.
  49. N. V. Thieu, Enoppy: A python library for engineering optimization problems (may 2023). doi:10.5281/zenodo.7953206.
  50. doi:10.1109/2.294849.
  51. doi:10.1109/ICNN.1995.488968.
  52. doi:10.1023/A:1008202821328.
  53. doi:10.1162/106365601750190398.
  54. doi:https://doi.org/10.1016/j.advengsoft.2013.12.007.
  55. doi:https://doi.org/10.1016/j.knosys.2015.12.022.
  56. doi:https://doi.org/10.1016/j.advengsoft.2016.01.008.
  57. doi:https://doi.org/10.1016/j.future.2019.02.028.
  58. doi:10.3390/math10101626.
  59. doi:https://doi.org/10.1016/j.matcom.2021.08.013.
  60. doi:https://doi.org/10.1016/j.neucom.2023.02.010. URL https://www.sciencedirect.com/science/article/pii/S0925231223001480
  61. doi:10.1155/2021/8548639.
  62. doi:10.1109/TPAMI.2021.3054824.
  63. arXiv:1412.6572.
  64. arXiv:1611.01236.
  65. arXiv:2003.01690.
  66. arXiv:1912.00049.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Rui Zhong (20 papers)
  2. Yuefeng Xu (3 papers)
  3. Chao Zhang (907 papers)
  4. Jun Yu (232 papers)
Citations (1)
View on Semantic Scholar