中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
STC-NAS: Fast neural architecture search with source-target consistency

文献类型：期刊论文

作者Sun, Zihao1,3; Hu, Yu1,2,3; Yang, Longxing1,3; Lu, Shun1,3; Mei, Jilin1,3; Han, Yinhe1,2,3; Li, Xiaowei2,3
刊名NEUROCOMPUTING
出版日期2022-08-01
卷号497页码:227-238
关键词Neural architecture search Consistency Automatic Jensen-Shannon divergence
ISSN号0925-2312
DOI10.1016/j.neucom.2021.11.082
英文摘要Neural architecture search (NAS) has shown very promising results for automatically designing network models. Most existing cell-based NAS approaches generate the target network model from a source super-network, which usually confront inconsistency issues. In this paper, we propose a new NAS method named STC-NAS, a fast neural architecture search with source-target consistency, so that not only the performance of the searched target model is improved but also the search process is boosted. Specifically, during the search phase, we sample the source super-network to let the samples be consistent with the target model. Moreover, we leverage the Jensen-Shannon divergence to ensure the samples are optimized in the direction of being more similar to the target model. Experimental results demonstrate that our method needs only 0.059 GPU-days to search on CIFAR-10. Benefited from its efficiency, STC-NAS can directly search the target super-network on the target task datasets, achieving 2.42% test error on CIFAR-10, 16.45% test error on CIFAR-100, and 24.2% test error on ImageNet datasets.(c) 2021 Elsevier B.V. All rights reserved.
资助项目National Key R&D Pro-gram of China[2018AAA0102701] ; State Key Laboratory of Computer Architecture (ICT, CAS)[CARCH5203]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000809908900001
出版者ELSEVIER
源URL[http://119.78.100.204/handle/2XEOYT63/19622]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Sun, Zihao
作者单位1.Chinese Acad Sci, Inst Comp Technol, Res Ctr Intelligent Comp Syst, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, Beijing 100190, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式
GB/T 7714		 Sun, Zihao,Hu, Yu,Yang, Longxing,et al. STC-NAS: Fast neural architecture search with source-target consistency[J]. NEUROCOMPUTING,2022,497:227-238.
APA Sun, Zihao.,Hu, Yu.,Yang, Longxing.,Lu, Shun.,Mei, Jilin.,...&Li, Xiaowei.(2022).STC-NAS: Fast neural architecture search with source-target consistency.NEUROCOMPUTING,497,227-238.
MLA Sun, Zihao,et al."STC-NAS: Fast neural architecture search with source-target consistency".NEUROCOMPUTING 497(2022):227-238.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。