Publication Type
Journal Article
Version
acceptedVersion
Publication Date
12-2021
Abstract
Recent breakthroughs in deep neural networks (DNNs) have fueled a tremendously growing demand for bringing DNN-powered intelligence into mobile platforms. While the potential of deploying DNNs on resource-constrained platforms has been demonstrated by DNN compression techniques, the current practice suffers from two limitations: 1) merely stand-alone compression schemes are investigated even though each compression technique only suit for certain types of DNN layers; and 2) mostly compression techniques are optimized for DNNs’ inference accuracy, without explicitly considering other application-driven system performance (e.g., latency and energy cost) and the varying resource availability across platforms (e.g., storage and processing capability). To this end, we propose AdaDeep, a usage-driven, automated DNN compression framework for systematically exploring the desired trade-off between performance and resource constraints, from a holistic system level. Specifically, in a layer-wise manner, AdaDeep automatically selects the most suitable combination of compression techniques and the corresponding compression hyperparameters for a given DNN. Thorough evaluations on six datasets and across twelve devices demonstrate that AdaDeep can achieve up to 18.6×18.6×18.6× latency reduction, 9.8×9.8×9.8× energy-efficiency improvement, and 37.3×37.3×37.3× storage reduction in DNNs while incurring negligible accuracy loss. Furthermore, AdaDeep also uncovers multiple novel combinations of compression techniques.
Keywords
Optimization, Mobile Computing, Mobile Handsets, Mobile Applications, Energy Storage, Measurement, Computational Modeling
Discipline
Artificial Intelligence and Robotics | Software Engineering
Research Areas
Software and Cyber-Physical Systems
Publication
IEEE Transactions on Mobile Computing
Volume
20
Issue
12
First Page
3282
Last Page
3297
ISSN
1536-1233
Identifier
10.1109/TMC.2020.2999956
Publisher
Institute of Electrical and Electronics Engineers
Citation
LIU, Sicong; DU, Junzhao; NAN, Kaiming; ZHOU, Zimu; LIU, Hui; WANG, Zhangyang; and LIN, Yingyan.
AdaDeep: A usage-driven, automated deep model compression framework for enabling ubiquitous intelligent mobiles. (2021). IEEE Transactions on Mobile Computing. 20, (12), 3282-3297.
Available at: https://ink.library.smu.edu.sg/sis_research/6648
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.ieeecomputersociety.org/10.1109/TMC.2020.2999956