Automating GAN Hyperparameter Selection: Insights from ‎The PSO and ABC Techniques

  • Authors

    • Azlee Zabidi Faculty of Computing, Universiti Malaysia Pahang, Al-Sultan Abdullah, Pekan, 26600, Malaysia
    • Hasliza Abu Hassan Faculty of Engineering and Life Sciences, Universiti Selangor, Bestari Jaya, 45500, Malaysia
    • Mazlina Abdul Majid Faculty of Computing, Universiti Malaysia Pahang, Al-Sultan Abdullah, Pekan, 26600, Malaysia
    • Syed Umar Armaghan Faculty of Computing, Universiti Malaysia Pahang, Al-Sultan Abdullah, Pekan, 26600, Malaysia
    • Siti Salwani Yaacob Faculty of Computing, Universiti Malaysia Pahang, Al-Sultan Abdullah, Pekan, 26600, Malaysia
    • Zairi Ismael Rizman Faculty of Electrical Engineering, Universiti Teknologi MARA, 23000 Dungun, Terengganu, Malaysia
    https://doi.org/10.14419/zrxyex74

    Received date: July 3, 2025

    Accepted date: August 8, 2025

    Published date: August 27, 2025

  • Artificial Bee Colony; Generative Adversarial Networks; Hyperparameter Optimization; Metaheuristic Algorithms; Particle Swarm Optimization‎.

  • Abstract

    Generative Adversarial Networks (GANs) are powerful deep learning models that generate high-quality synthetic data for picture synthesis, ‎data augmentation, and video production. However, training GANs is difficult and resource-intensive because of non-convergence, mode ‎collapse, instability, and hyperparameter sensitivity. This research optimizes hyperparameters utilizing optimization methods to improve ‎GAN, with an experiment applying to digit dataset generation. Hybrid Particle Swarm Optimization (PSO) and Artificial Bee Colony (ABC) ‎algorithms were presented to automate hyperparameter tweaking, focusing on Training Epochs, Batch Size, and Label Smoothing. This ‎work introduced binarizing feature candidate selection instead of discrete values for optimization. This method represents parameters in ‎binary form, where 1 signifies selection and 0 indicates non-selection, for more efficient parameter space search. Through experimental ‎findings, the proposed technique significantly improves GAN training stability and output quality. Training for 25 epochs, with a batch size ‎of 128 and a label smoothing of 0.8, yields the most consistent and high-quality outcomes, with ABC surpassing PSO. This study ‎underscores the effect of hyperparameter optimization for enhancing GAN performance and introduces an innovative way for adjusting ‎critical parameters. Optimization methods like PSO and ABC can improve GAN training and support their use in digit generation and other ‎applications‎.

  • References

    1. I. J. Goodfellow, J. P.-Abadie, M. Mirza, B. Xu, D. W.-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative Adversarial Nets,” Advances in Neural Information Processing Systems, vol. 27, pp. 1-9, 2014.
    2. T. Karras, S. Laine, and T. Aila, “A Style-Based Generator Architecture for Generative Adversarial Networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence vol. 43, no. 12, pp. 4217–4228, Dec. 2018. https://doi.org/10.1109/TPAMI.2020.2970919.
    3. T. Salimans, I. Goodfellow, W. Zaremba, V. Cheung, A. Radford, and X. Chen, “Improved Techniques for Training GANs,” Advances in Neural Information Processing Systems, vol. 29, pp. 1-9, 2016.
    4. M. Lucic, K. Kurach, M. M. Google, B. O. Bousquet, and S. Gelly, “Are GANs Created Equal? A Large-Scale Study,” Advances in Neural Infor-mation Processing Systems, vol. 31, pp. 1-10, 2018.
    5. L. Mescheder, A. Geiger, and S. Nowozin, “Which Training Methods for GANs do actually Converge?,” International Conference on Machine Learning, pp. 3481-3490.
    6. J. Kennedy and R. Eberhart, “Particle swarm optimization,” International Conference on Neural Networks, vol. 4, pp. 1942–1948. https://doi.org/10.1109/ICNN.1995.488968.
    7. D. Karaboga and B. Basturk, “A powerful and efficient algorithm for numerical function optimization: Artificial bee colony (ABC) algorithm,” Journal of Global Optimization, vol. 39, no. 3, pp. 459–471, Nov. 2007. https://doi.org/10.1007/s10898-007-9149-x.
    8. C. F. Chen, A. Mohd Zain, L. P. Mo, and K. Q. Zhou, “A New Hybrid Algorithm Based on ABC and PSO for Function Optimization,” IOP Con-ference Series: Materials Science and Engineering, vol. 864, no. 1, p. 012065. Jul. 2020. https://doi.org/10.1088/1757-899X/864/1/012065.
    9. D. Freitas, L. G. Lopes, and F. Morgado-Dias, “Particle Swarm Optimisation: A Historical Review Up to the Current Developments,” Entropy, vol. 22, no. 3, p. 362, Mar. 2020. https://doi.org/10.3390/e22030362.
    10. L. Tian, Z. Wang, W. Liu, Y. Cheng, F. E. Alsaadi, and X. Liu, “Empower parameterized generative adversarial networks using a novel particle swarm optimizer: algorithms and applications,” International Journal of Machine Learning and Cybernetics, vol. 13, no. 4, pp. 1145–1155, Apr. 2022. https://doi.org/10.1007/s13042-021-01440-3.
    11. D. Karaboga, B. Gorkemli, C. Ozturk, and N. Karaboga, “A comprehensive survey: Artificial bee colony (ABC) algorithm and applications,” Arti-ficial Intelligence Review, vol. 42, no. 1, pp. 21–57, Mar. 2014. https://doi.org/10.1007/s10462-012-9328-0.
    12. K. G. Shreeharsha, C. G. Korde, M. H. Vasantha, and Y. B. Nithin Kumar, “Training of Generative Adversarial Networks using Particle Swarm Optimization Algorithm,” IEEE International Symposium on Smart Electronic Systems, pp. 127–130, 2021. https://doi.org/10.1109/iSES52644.2021.00038.
    13. Y. Kossale, M. Airaj, and A. Darouichi, “Mode Collapse in Generative Adversarial Networks: An Overview,” IEEE 8th International Conference on Optimization and Applications, pp. 1-6 2022. https://doi.org/10.1109/ICOA55659.2022.9934291.
    14. T. Miyato, T. Kataoka, M. Koyama, and Y. Yoshida, “Spectral Normalization for Generative Adversarial Networks,” 6th International Conference on Learning Representations, pp. 1-26, Feb. 2018.
    15. M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein Generative Adversarial Networks,” International Conference on Machine Learning, pp. 214-223, 2017.
    16. P. K. Saluja and D. Vathana, “Rectifying Mode Collapse in GANs,” International Conference on Applied Artificial Intelligence and Computing, pp. 1718–1722, 2022. https://doi.org/10.1109/ICAAIC53929.2022.9792861.
    17. T. Karras, T. Aila, S. Laine, and J. Lehtinen, “Progressive Growing of GANs for Improved Quality, Stability, and Variation,” 6th International Conference on Learning Representations, pp. 1-26, Oct. 2017.
    18. K. Mangalam and R. Garg, “Overcoming Mode Collapse with Adaptive Multi Adversarial Training,” 32nd British Machine Vision Conference, pp. 1-19, Apr. 2025.
    19. L. A. Courtenay and D. González-Aguilera, “Geometric Morphometric Data Augmentation Using Generative Computational Learning Algorithms,” Applied Sciences, vol. 10, no. 24, p. 9133, Dec. 2020. https://doi.org/10.3390/app10249133.
    20. X. Ma, R. Jin, K. A. Sohn, J. Y. Paik, and T. S. Chung, “An Adaptive Control Algorithm for Stable Training of Generative Adversarial Networks,” IEEE Access, vol. 7, pp. 184103–184114, 2019. https://doi.org/10.1109/ACCESS.2019.2960461.
    21. H. Zhang, I. Goodfellow, D. Metaxas, and A. Odena, “Self-Attention Generative Adversarial Networks,” International Conference on Machine Learning, pp. 7354-7363. 2019.
    22. Z. Liu, P. Luo, X. Wang, and X. Tang, “Deep Learning Face Attributes in the Wild,” IEEE International Conference on Computer Vision, pp. 3730-3738. 2015. https://doi.org/10.1109/ICCV.2015.425.
    23. C. Wang, C. Xu, X. Yao, and D. Tao, “Evolutionary generative adversarial networks,” IEEE Transactions on Evolutionary Computation, vol. 23, no. 6, pp. 921–934, Dec. 2019. https://doi.org/10.1109/TEVC.2019.2895748.
    24. X. S. Yang, Nature-inspired optimization algorithms. Academic Press, 2020. https://doi.org/10.1016/B978-0-12-821986-7.00013-5.
    25. S. Katoch, S. S. Chauhan, and V. Kumar, “A review on genetic algorithm: Past, present, and future,” Multimedia Tools and Applications, vol. 80, no. 5, pp. 8091–8126, Feb. 2021. https://doi.org/10.1007/s11042-020-10139-6.
    26. S. Mohammadi and S. R. Hejazi, “Using particle swarm optimization and genetic algorithms for optimal control of non-linear fractional-order cha-otic system of cancer cells,” Mathematics and Computers in Simulation, vol. 206, pp. 538–560, Apr. 2023. https://doi.org/10.1016/j.matcom.2022.11.023.
    27. H. Aoyang, Z. Shengqi, J. Xuehui, and Z. Zhisheng, “Short-term Load Forecasting Model Based on RBF Neural Network Optimized by Artificial Bee Colony Algorithm,” IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering, pp. 486–489, Mar. 2021. https://doi.org/10.1109/ICBAIE52039.2021.9390043.
    28. Z. Li, K. Chen, and J. Wang, “An adaptive environmental sampling path planning technique for autonomous underwater vehicles based on ant col-ony optimization algorithm,” IEEE 4th International Conference on Civil Aviation Safety and Information Technology, pp. 727–730, 2022. https://doi.org/10.1109/ICCASIT55263.2022.9987183.
    29. T. Kurban, P. Civicioglu, R. Kurban, and E. Besdok, “Comparison of evolutionary and swarm based computational techniques for multilevel color image thresholding,” Applied Soft Computing, vol. 23, pp. 128–143, Oct. 2014. https://doi.org/10.1016/j.asoc.2014.05.037.
    30. D. Karaboga and C. Ozturk, “A novel clustering approach: Artificial Bee Colony (ABC) algorithm,” Applied Soft Computing, vol. 11, no. 1, pp. 652–657, Jan. 2011. https://doi.org/10.1016/j.asoc.2009.12.025.
    31. J. Tang, G. Liu, and Q. Pan, “A Review on Representative Swarm Intelligence Algorithms for Solving Optimization Problems: Applications and Trends,” IEEE/CAA Journal of Automatica Sinica, vol. 8, no. 10, pp. 1627–1643, Oct. 2021. https://doi.org/10.1109/JAS.2021.1004129.
    32. A. Radford, L. Metz, and S. Chintala, “Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks,” 4th International Conference on Learning Representations, pp. 1-16, Nov. 2015.

  • Downloads

  • How to Cite

    Zabidi, A. ., Abu Hassan, H. ., Abdul Majid, M. ., Armaghan, S. U. ., Yaacob, S. S. ., & Rizman, Z. I. (2025). Automating GAN Hyperparameter Selection: Insights from ‎The PSO and ABC Techniques. International Journal of Basic and Applied Sciences, 14(4), 763-772. https://doi.org/10.14419/zrxyex74