论文标题
离散化感知的体系结构搜索
Discretization-Aware Architecture Search
论文作者
论文摘要
神经体系结构搜索（NAS）的搜索成本已通过体重分担方法大大降低。这些方法通过所有可能的边缘和操作优化了一个超级网络，并通过离散化确定最佳子网，\ textit {i.e。}，修剪弱候选人。在操作或边缘上执行的离散化过程会造成严重的不准确性，因此不能保证最终体系结构的质量。本文介绍了离散化的体系结构搜索（da \ textsuperscript {2} s），其核心想法是添加损失术语，将超级网络推向所需拓扑的配置，以使离散化带来的准确性损失在很大程度上减轻了。标准图像分类基准的实验证明了我们方法的优势，特别是在以前未研究的目标网络配置下。
The search cost of neural architecture search (NAS) has been largely reduced by weight-sharing methods. These methods optimize a super-network with all possible edges and operations, and determine the optimal sub-network by discretization, \textit{i.e.}, pruning off weak candidates. The discretization process, performed on either operations or edges, incurs significant inaccuracy and thus the quality of the final architecture is not guaranteed. This paper presents discretization-aware architecture search (DA\textsuperscript{2}S), with the core idea being adding a loss term to push the super-network towards the configuration of desired topology, so that the accuracy loss brought by discretization is largely alleviated. Experiments on standard image classification benchmarks demonstrate the superiority of our approach, in particular, under imbalanced target network configurations that were not studied before.
