Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices

doi:10.1109/TCAD.2020.3013050

	Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices
	Li, Guangli 1,2; Ma, Xiu 3; Wang, Xueying 1,2; Liu, Lei 1,2; Xue, Jingling 4; Feng, Xiaobing 1,2
	2020-11-01
发表期刊	IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS
ISSN	0278-0070
卷号	39 期号:11 页码:3614-3626
摘要	The increasing computational cost of deep neural network models limits the applicability of intelligent applications on resource-constrained edge devices. While a number of neural network pruning methods have been proposed to compress the models, prevailing approaches focus only on parametric operators (e.g., convolution), which may miss optimization opportunities. In this article, we present a novel fusion-catalyzed pruning approach, called FUPRUNER, which simultaneously optimizes the parametric and nonparametric operators for accelerating neural networks. We introduce an aggressive fusion method to equivalently transform a model, which extends the optimization space of pruning and enables nonparametric operators to be pruned in a similar manner as parametric operators, and a dynamic filter pruning method is applied to decrease the computational cost of models while retaining the accuracy requirement. Moreover, FUPRUNER provides configurable optimization options for controlling fusion and pruning, allowing much more flexible performance-accuracy tradeoffs to be made. Evaluation with state-of-the-art residual neural networks on five representative intelligent edge platforms, Jetson TX2, Jetson Nano, Edge tensor processing unit, neural compute stick, and neural compute stick 2, demonstrates the effectiveness of our approach, which can accelerate the inference of models on CIFAR-10 and ImageNet datasets.
关键词	Deep learning system edge intelligence model compression and acceleration neural networks
DOI	10.1109/TCAD.2020.3013050
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2017YFB1003103] ; Science Fund for Creative Research Groups of the National Natural Science Foundation of China[61521092] ; Australian Research Council[DP170103956] ; Australian Research Council[DP180104069]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Interdisciplinary Applications ; Engineering, Electrical & Electronic
WOS记录号	WOS:000587712700039
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：28[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/15995
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Liu, Lei
作者单位	1.Chinese Acad Sci, Inst Comp Technol, State Key Lab Comp Architecture, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Sch Comp Sci & Technol, Beijing 100190, Peoples R China 3.Jilin Univ, Coll Comp Sci & Technol, Changchun 130012, Peoples R China 4.Univ New South Wales, Sch Comp Sci & Engn, Sydney, NSW 2052, Australia
推荐引用方式 GB/T 7714	Li, Guangli,Ma, Xiu,Wang, Xueying,et al. Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices[J]. IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS,2020,39(11):3614-3626.
APA	Li, Guangli,Ma, Xiu,Wang, Xueying,Liu, Lei,Xue, Jingling,&Feng, Xiaobing.(2020).Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices.IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS,39(11),3614-3626.
MLA	Li, Guangli,et al."Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices".IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS 39.11(2020):3614-3626.