Neural Architecture Search is a costly practice. The fact that a search space can span a vast number of design choices with each architecture evaluation taking nontrivial overhead makes it hard for an algorithm to sufficiently explore candidate networks. In this paper, we propose AutoBuild, a scheme which learns to align the latent embeddings of operations and architecture modules with the ground-truth performance of the architectures they appear in. By doing so, AutoBuild is capable of assigning interpretable importance scores to architecture modules, such as individual operation features and larger macro operation sequences such that high-performance neural networks can be constructed without any need for search. Through experiments performed on state-of-the-art image classification, segmentation, and Stable Diffusion models, we show that by mining a relatively small set of evaluated architectures, AutoBuild can learn to build high-quality architectures directly or help to reduce search space to focus on relevant areas, finding better architectures that outperform both the original labeled ones and ones found by search baselines. Code available at https://github.com/Ascend-Research/AutoBuild

翻译：神经架构搜索是一种成本高昂的方法。由于搜索空间可能涵盖大量设计选择，且每次架构评估都需要显著的开销，这使得算法难以充分探索候选网络。在本文中，我们提出AutoBuild方案，该方案学习将操作和架构模块的潜在嵌入与其所在架构的真实性能对齐。通过这种方式，AutoBuild能够为架构模块（如单个操作特征和更大的宏观操作序列）分配可解释的重要性分数，从而无需搜索即可构建高性能神经网络。在最新的图像分类、分割和Stable Diffusion模型上进行的实验表明，通过挖掘相对较少的已评估架构集，AutoBuild可以直接学习构建高质量架构，或帮助缩小搜索空间以聚焦相关区域，从而找到优于原始标记架构及搜索基线所发现架构的更优架构。代码可在https://github.com/Ascend-Research/AutoBuild获取。