The evolutionary paradigm has been successfully applied to neural network search(NAS) in recent years. Due to the vast search complexity of the global space, current research mainly seeks to repeatedly stack partial architectures to build the entire model or to seek the entire model based on manually designed benchmark modules. The above two methods are attempts to reduce the search difficulty by narrowing the search space. To efficiently search network architecture in the global space, this paper proposes another solution, namely a computationally efficient neural architecture evolutionary search framework based on network growth (G-EvoNAS). The complete network is obtained by gradually deepening different Blocks. The process begins from a shallow network, grows and evolves, and gradually deepens into a complete network, reducing the search complexity in the global space. Then, to improve the ranking accuracy of the network, we reduce the weight coupling of each network in the SuperNet by pruning the SuperNet according to elite groups at different growth stages. The G-EvoNAS is tested on three commonly used image classification datasets, CIFAR10, CIFAR100, and ImageNet, and compared with various state-of-the-art algorithms, including hand-designed networks and NAS networks. Experimental results demonstrate that G-EvoNAS can find a neural network architecture comparable to state-of-the-art designs in 0.2 GPU days.

翻译：进化范式近年来已成功应用于神经网络架构搜索（NAS）。由于全局空间的搜索复杂性极高，当前研究主要通过重复堆叠局部架构构建完整模型，或基于人工设计的基准模块搜索完整模型。上述两种方法旨在通过缩小搜索空间来降低搜索难度。为在全局空间中高效搜索网络架构，本文提出另一种解决方案，即一种基于网络增长的计算高效神经架构进化搜索框架（G-EvoNAS）。该框架通过逐步深化不同模块（Block）来生成完整网络，其过程从浅层网络开始，经历生长与进化，逐步深化为完整网络，从而降低全局空间的搜索复杂度。随后，为提升网络排序精度，我们根据不同生长阶段的精英群体对超网（SuperNet）进行剪枝，以此减少超网中各网络的权重耦合。G-EvoNAS在CIFAR10、CIFAR100和ImageNet三个常用图像分类数据集上进行测试，并与多种最新算法（包括人工设计网络和NAS网络）进行对比。实验结果表明，G-EvoNAS可在0.2个GPU天内找到与最新设计性能相当的神经网络架构。