用于高效图像分类器搜索的广义全局排名感知神经结构排名器
Generalized Global Ranking-Aware Neural Architecture Ranker for Efficient Image Classifier Search
摘要：
神经结构搜索（NAS）是一个强大的工具，自动化有效的图像处理DNN的设计。该排序方法被用来设计一个有效的NAS性能预测器。前面的对比方法通过比较体系结构对并预测它们的相对性能来解决排名问题。然而，它只关注两个相关架构之间的排名，而忽略了搜索空间的整体质量分布，这可能会遇到泛化问题。提出了一种基于神经网络结构排序器（NAR）的预测器，该预测器集中于特定结构的全局质量层，以解决局部视角引起的问题。NAR在全局范围内探索搜索空间的质量层，并根据其全局排名将每个人分类到他们所属的层。因此，预测器获得搜索空间的性能分布的知识，这有助于更容易地将其排名能力推广到数据集。同时，全局质量分布通过根据质量等级的统计直接对候选者进行采样来促进搜索阶段，这无需训练搜索算法，例如，强化学习（RL）或进化算法（EA），因此它简化了NAS管道并节省了计算开销。建议的NAR实现更好的性能比国家的最先进的方法在两个广泛使用的数据集NAS研究。在NAS-Bench-101的巨大搜索空间上，NAR仅通过采样就可以轻松找到具有最高0.01 $\unicode{x2030}$性能的架构。它也很好地推广到NAS-Bench-201的不同图像数据集，即，CIFAR-10，CIFAR-100和ImageNet-16-120，通过识别每个架构的最佳架构。
英文摘要：
Neural Architecture Search (NAS) is a powerful tool for automating effective image processing DNN designing. The ranking has been advocated to design an efficient performance predictor for NAS. The previous contrastive method solves the ranking problem by comparing pairs of architectures and predicting their relative performance. However, it only focuses on the rankings between two involved architectures and neglects the overall quality distributions of the search space, which may suffer generalization issues. A predictor, namely Neural Architecture Ranker (NAR) which concentrates on the global quality tier of specific architecture, is proposed to tackle such problems caused by the local perspective. The NAR explores the quality tiers of the search space globally and classifies each individual to the tier they belong to according to its global ranking. Thus, the predictor gains the knowledge of the performance distributions of the search space which helps to generalize its ranking ability to the datasets more easily. Meanwhile, the global quality distribution facilitates the search phase by directly sampling candidates according to the statistics of quality tiers, which is free of training a search algorithm, e.g., Reinforcement Learning (RL) or Evolutionary Algorithm (EA), thus it simplifies the NAS pipeline and saves the computational overheads. The proposed NAR achieves better performance than the state-of-the-art methods on two widely used datasets for NAS research. On the vast search space of NAS-Bench-101, the NAR easily finds the architecture with top 0.01$\unicode{x2030}$ performance only by sampling. It also generalizes well to different image datasets of NAS-Bench-201, i.e., CIFAR-10, CIFAR-100, and ImageNet-16-120 by identifying the optimal architectures for each of them.
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。
