Neural architecture search (NAS) automates neural network design, improving efficiency over manual approaches. However, efficiently discovering high-performance neural network architectures that simultaneously optimize multiple objectives remains a significant challenge in NAS. Existing methods often suffer from limited population diversity and inadequate exploration of the search space, particularly in regions with extreme complexity values. To address these challenges, we propose MOEA-BUS, an innovative multi-objective evolutionary algorithm based on bi-population with uniform sampling for neural architecture search, aimed at simultaneously optimizing both accuracy and network complexity. In MOEA-BUS, a novel uniform sampling method is proposed to initialize the population, ensuring that architectures are distributed uniformly across the objective space. Furthermore, to enhance exploration, we deploy a bi-population framework where two populations evolve synergistically, facilitating comprehensive search space coverage. Experiments on CIFAR-10 and ImageNet demonstrate MOEA-BUS's superiority, achieving top-1 accuracies of 98.39% on CIFAR-10, and 80.03% on ImageNet. Notably, it achieves 78.28% accuracy on ImageNet with only 446M MAdds. Ablation studies confirm that both uniform sampling and bi-population mechanisms enhance population diversity and performance. Additionally, in terms of the Kendall's tau coefficient, the SVM achieves an improvement of at least 0.035 compared to the other three commonly used machine learning models, and uniform sampling provided an enhancement of approximately 0.07.

翻译：神经架构搜索（NAS）自动化了神经网络设计，相比手动方法提高了效率。然而，在NAS中，如何高效地发现同时优化多个目标的高性能神经网络架构仍然是一个重大挑战。现有方法通常存在种群多样性有限和搜索空间探索不足的问题，尤其是在具有极端复杂度值的区域。为应对这些挑战，我们提出了MOEA-BUS，一种创新的基于双种群均匀采样的多目标进化算法，用于神经架构搜索，旨在同时优化准确性和网络复杂度。在MOEA-BUS中，提出了一种新颖的均匀采样方法来初始化种群，确保架构在目标空间中均匀分布。此外，为增强探索能力，我们部署了一个双种群框架，其中两个种群协同进化，促进对搜索空间的全面覆盖。在CIFAR-10和ImageNet上的实验证明了MOEA-BUS的优越性，在CIFAR-10上达到了98.39%的top-1准确率，在ImageNet上达到了80.03%。值得注意的是，在仅使用446M MAdds的情况下，其在ImageNet上实现了78.28%的准确率。消融研究证实，均匀采样和双种群机制均能增强种群多样性和性能。此外，就Kendall's tau系数而言，SVM相比其他三种常用机器学习模型至少提升了0.035，而均匀采样则带来了约0.07的提升。