论文标题
任务感知的神经架构搜索
Task-Aware Neural Architecture Search
论文作者
论文摘要
手工神经网络的设计需要大量时间和资源。事实证明，神经体系结构搜索（NAS）的最新技术比传统手工设计具有竞争力或更好，尽管它们需要域知识，并且通常使用有限的搜索空间。在本文中，我们提出了一个新颖的神经结构搜索框架，利用基本任务模型的字典以及目标任务与词典的原子之间的相似性。因此，基于字典的基本模型生成自适应搜索空间。通过引入基于梯度的搜索算法，我们可以在不完全培训网络的情况下评估和发现搜索空间中最佳的体系结构。实验结果表明我们提出的任务感知方法的功效。
The design of handcrafted neural networks requires a lot of time and resources. Recent techniques in Neural Architecture Search (NAS) have proven to be competitive or better than traditional handcrafted design, although they require domain knowledge and have generally used limited search spaces. In this paper, we propose a novel framework for neural architecture search, utilizing a dictionary of models of base tasks and the similarity between the target task and the atoms of the dictionary; hence, generating an adaptive search space based on the base models of the dictionary. By introducing a gradient-based search algorithm, we can evaluate and discover the best architecture in the search space without fully training the networks. The experimental results show the efficacy of our proposed task-aware approach.
