Neural Architecture Search (NAS) has become a pivotal technique in automated machine learning. Evolutionary Algorithm (EA)-based methods demonstrate superior search quality but suffer from prohibitive computational costs, while gradient-based approaches like DARTS offer high efficiency but are prone to premature convergence and performance collapse. To bridge this gap, we propose G-ICSO-NAS, a hybrid framework implementing a three-stage optimization strategy. The Warm-up Phase pre-trains supernet weights ($w$) via differentiable methods while architecture parameters ($α$) remain frozen. The Exploration Phase adopts a hybrid co-optimization mechanism: an Improved Competitive Swarm Optimizer (ICSO) with diversity-aware fitness navigates the architecture space to update $α$, while gradient descent concurrently updates $w$. The Stability Phase employs fine-grained gradient-based search with early stopping to converge to the optimal architecture. By synergizing ICSO's global navigation capability with differentiable methods' efficiency, G-ICSO-NAS achieves remarkable performance with minimal cost. In the context of the DARTS search space, an accuracy of 97.46\% is achieved on CIFAR-10 with a computational budget of just 0.15 GPU-Days. The method also exhibits strong transfer potential, recording accuracies of 83.1\% (CIFAR-100) and 75.02\% (ImageNet). Furthermore, regarding the NAS-Bench-201 benchmark, G-ICSO-NAS is shown to deliver state-of-the-art results across all evaluated datasets.

翻译：神经架构搜索（NAS）已成为自动机器学习中的关键技术。基于进化算法（EA）的方法展现出优异的搜索质量，但面临高昂的计算成本；而基于梯度的方法（如DARTS）虽具有高效率，却容易陷入早熟收敛和性能崩溃。为弥合这一差距，我们提出G-ICSO-NAS，一种实现三阶段优化策略的混合框架。热身阶段通过可微分方法预训练超级网络权重（$w$），同时冻结架构参数（$α$）。探索阶段采用混合协同优化机制：具有多样性感知能力的改进竞争群优化器（ICSO）在架构空间中导航以更新$α$，而梯度下降则同步更新$w$。稳定阶段采用带有早停策略的细粒度梯度搜索，收敛至最优架构。通过将ICSO的全局导航能力与可微分方法的高效性相结合，G-ICSO-NAS以极低代价实现了卓越性能。在DARTS搜索空间背景下，该方法仅以0.15 GPU天的计算预算即在CIFAR-10上达到97.46%的准确率。该方法还展现出强大的迁移潜力，在CIFAR-100和ImageNet上分别取得83.1%和75.02%的准确率。此外，在NAS-Bench-201基准测试中，G-ICSO-NAS在所有评估数据集上均取得了最先进的结果。