arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.00219cs.LG
收藏

面向不同预算的Pareto边界感知神经结构生成

Pareto-Frontier-aware Neural Architecture Generation for Diverse Budgets

School of Software Engineering, South China University of Technology(华南理工大学软件学院);Weixin Group, Tencent(腾讯微信事业群);Tencent AI Lab, Tencent(腾讯AI实验室)

Yong Guo, Yaofo Chen, Yin Zheng, Qi Chen, Peilin Zhao, Jian Chen, Junzhou Huang, Mingkui Tan

摘要:

在不同应用/设备所产生的不同计算预算下设计可行且有效的架构对于在实践中部署深度模型至关重要。现有的方法往往执行一个独立的架构搜索为每个目标预算,这是非常低效的,但不必要的。此外,重复的独立搜索方式不可避免地忽略了不同搜索过程之间的共同知识,影响了搜索性能。为了解决这些问题,我们寻求训练一个通用的架构生成器,自动产生有效的架构,任意预算,仅仅通过模型推理。为此,我们提出了一个帕累托边界感知神经架构生成器(NAG),它以任意的预算作为输入,并为目标预算产生帕累托最优架构。我们通过学习帕累托边界(即,帕累托最优体系结构的集合)相对于模型性能和计算成本(例如,等待时间)。在三个平台上进行了广泛的实验(即,移动,CPU和GPU)显示了所提出的方法优于现有的NAS方法。

英文摘要:

Designing feasible and effective architectures under diverse computation budgets incurred by different applications/devices is essential for deploying deep models in practice. Existing methods often perform an independent architecture search for each target budget, which is very inefficient yet unnecessary. Moreover, the repeated independent search manner would inevitably ignore the common knowledge among different search processes and hamper the search performance. To address these issues, we seek to train a general architecture generator that automatically produces effective architectures for an arbitrary budget merely via model inference. To this end, we propose a Pareto-Frontier-aware Neural Architecture Generator (NAG) which takes an arbitrary budget as input and produces the Pareto optimal architecture for the target budget. We train NAG by learning the Pareto frontier (i.e., the set of Pareto optimal architectures) over model performance and computational cost (e.g., latency). Extensive experiments on three platforms (i.e., mobile, CPU, and GPU) show the superiority of the proposed method over existing NAS methods.

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。

↑