G-EvoNAS：基于网络增长的进化神经架构搜索
G-EvoNAS: Evolutionary Neural Architecture Search Based on Network Growth
AI总结：
本文提出基于网络增长的进化神经架构搜索框架 G-EvoNAS，通过逐步加深 Block 和分阶段精英剪枝降低全局搜索复杂度，仅用 0.2 GPU 天即可获得媲美最先进方法的图像分类网络。
摘要：
近年来，进化范式已成功应用于神经网络搜索（NAS）。由于全局空间的搜索复杂度极高，当前研究主要寻求重复堆叠局部架构来构建完整模型，或基于人工设计的基准模块来寻找完整模型。上述两种方法都是通过缩小搜索空间来降低搜索难度的尝试。为在全局空间中高效搜索网络架构，本文提出了另一种解决方案，即基于网络增长的计算高效型神经架构进化搜索框架（G-EvoNAS）。完整网络通过逐步加深不同的 Block 获得。该过程从浅层网络开始，进行增长和进化，并逐步加深为完整网络，从而降低全局空间中的搜索复杂度。随后，为提高网络的排序准确性，我们根据不同增长阶段的精英群体对 SuperNet 进行剪枝，以减少 SuperNet 中各网络的权重耦合。G-EvoNAS 在三个常用图像分类数据集 CIFAR10、CIFAR100 和 ImageNet 上进行了测试，并与包括人工设计网络和 NAS 网络在内的多种最先进算法进行了比较。实验结果表明，G-EvoNAS 能够在 0.2 GPU 天内找到可与最先进设计相媲美的神经网络架构。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
