In-Situ NAS: A Plug-and-Search Neural Architecture Search Framework Across Hardware Platforms

doi:10.1109/TC.2025.3569161

	In-Situ NAS: A Plug-and-Search Neural Architecture Search Framework Across Hardware Platforms
	Lv, Hao 1,2; Zhang, Lei 1; Wang, Ying 2,3
	2025-09-01
发表期刊	IEEE TRANSACTIONS ON COMPUTERS
ISSN	0018-9340
卷号	74 期号:9 页码:2856-2869
摘要	Hardware-aware Neural Architecture Search (HW-NAS) has garnered significant research interest due to its ability to automate the design of neural networks for various hardware platforms. Prevalent HW-NAS frameworks often use fast predictors to estimate network performance, bypassing the time-consuming actual profiling step. However, the resource-intensive nature of building these predictors and their accuracy limitations hinder their practical use in diverse deployment scenarios. In response, we emphasize the indispensable role of actual profiling in HW-NAS and explore efficiency optimization possibilities within the HW-NAS framework. We provide a systematic analysis of profiling overhead in HW-NAS and identify many redundant and unnecessary operations during the search phase. We then optimize the workflow and present In-situ NAS, which leverages similarity features and exploration history to eliminate redundancy and improve runtime efficiency. In-situ NAS also offers simplified interfaces to ease the user's effort in managing the complex device-dependent profiling flow, enabling plug-and-search functionality across diverse hardware platforms. Experimental results show that In-situ NAS achieves an average 10x speedup across different hardware platforms while reducing the search overhead by 8x compared to predictor-based approaches in various deployment scenarios. Additionally, In-situ NAS consistently discovers networks with better accuracy (about 1.5%) across diverse hardware platforms compared to predictor-based NAS.
关键词	Neural architecture search deep learning optimization hardware-aware AutoML performance evaluation Neural architecture search deep learning optimization hardware-aware AutoML performance evaluation
DOI	10.1109/TC.2025.3569161
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[NSFC.62222411] ; National Key R&D Program of China[2023YFB4404400]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Hardware & Architecture ; Engineering, Electrical & Electronic
WOS记录号	WOS:001550784800011
出版者	IEEE COMPUTER SOC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/41777
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wang, Ying
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 101408, Peoples R China 3.Chinese Acad Sci, State Key Lab Comp Architecture, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Lv, Hao,Zhang, Lei,Wang, Ying. In-Situ NAS: A Plug-and-Search Neural Architecture Search Framework Across Hardware Platforms[J]. IEEE TRANSACTIONS ON COMPUTERS,2025,74(9):2856-2869.
APA	Lv, Hao,Zhang, Lei,&Wang, Ying.(2025).In-Situ NAS: A Plug-and-Search Neural Architecture Search Framework Across Hardware Platforms.IEEE TRANSACTIONS ON COMPUTERS,74(9),2856-2869.
MLA	Lv, Hao,et al."In-Situ NAS: A Plug-and-Search Neural Architecture Search Framework Across Hardware Platforms".IEEE TRANSACTIONS ON COMPUTERS 74.9(2025):2856-2869.