On-Demand Deep Model Compression for Mobile Devices: A Usage-Driven Model Selection Framework
Open accessAbstract
Recent research has demonstrated the potential of deploying deep neural networks (DNNs) on resource-constrained mobile platforms by trimming down the network complexity using different compression techniques. The current practice only investigate stand-alone compression schemes even though each compression technique may be well suited only for certain types of DNN layers. Also, these compression techniques are optimized merely for the inference accuracy of DNNs, without explicitly considering other application-driven system performance (e.g. latency and energy cost) and the varying resource availabilities across platforms (e.g. storage and processing capability). In this paper, we explore the desirable tradeoff between performance and resource constraints by user-specified needs, from a holistic system-level viewpoint. Specifically, we develop a usage-driven selection framework, referred to as AdaDeep, to automatically select a combination of compression techniques for a given DNN, that will lead to an optimal balance between user-specified performance goals and resource constraints. With an extensive evaluation on five public datasets and across twelve mobile devices, experimental results show that AdaDeep enables up to 9.8x latency reduction, 4.3x energy efficiency improvement, and 38x storage reduction in DNNs while incurring negligible accuracy loss. AdaDeep also uncovers multiple effective combinations of compression techniques unexplored in existing literature.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
AdaDeep formulates goals and constraints on accuracy, latency, storage, and energy into a unified optimization problem and uses DRL to find a good combination of compression techniques.
“the proposed automatic optimization framework AdaDeep [75] systematically formulates the goals and constraints on accuracy, latency, storage, and energy into a unified optimization problem and leverages DRL to effectively find a good combination of compression techniques.”
From Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing (2019) · cites this paper as [75]
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · see citing works
Playing Atari with Deep Reinforcement Learning
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Riedmiller, M. (2013) · arXiv · doi:10.48550/arxiv.1312.5602 · Cited by 9,471 · see citing works
Practical Bayesian Optimization of Machine Learning Algorithms
Snoek, J., Larochelle, H., & Adams, R. P. (2012) · arXiv · doi:10.48550/arxiv.1206.2944 · Cited by 6,691 · see citing works
Efficient Processing of Deep Neural Networks: A Tutorial and Survey
Sze, V., Chen, Y.-H., Yang, T.-J., & Emer, J. S. (2017) · Proceedings of the IEEE · doi:10.1109/jproc.2017.2761740 · Cited by 4,215 · cited 2× · see citing works
“Compression is a commonly employed technique to trim down the complexity of DNNs, which can be performed by reducing the weight precision, or the number of operations, or both [41].”
BackgroundMethodDeep Reinforcement Learning with Double Q-Learning
Van Hasselt, H., Guez, A., & Silver, D. (2016) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v30i1.10295 · Cited by 3,318 · see citing works
Designing Energy-Efficient Convolutional Neural Networks Using Energy-Aware Pruning
Yang, T.-J., Chen, Y.-H., & Sze, V. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.643 · Cited by 732 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing
Zhou, Z., Chen, X., Li, E., Zeng, L., Luo, K., & Zhang, J. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2918951 · Cited by 2,455 · see citing works
“To this end, the proposed automatic optimization framework AdaDeep [75] systematically formulates the goals and constraints on accuracy, latency, storage, and energy into a unified optimization problem and leverages DRL to effectively find a good combination of compression techniques.”
MethodSelf-citationDeep Learning With Edge Computing: A Review
Chen, J., & Ran, X. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2921977 · Cited by 1,540 · see citing works
Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
Wang, X., Han, Y., Leung, V. C. M., Niyato, D., Yan, X., & Chen, X. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2970550 · Cited by 1,498 · see citing works
“AdaDeep [149] explores the desirable balance between performance and resource constraints, and based on DRL, automatically selects various compression techniques (such as model pruning) to form a compressed model according to current available resources, thus fully utilizing the advantages of them.”
MethodEdge Assisted Real-time Object Detection for Mobile Augmented Reality
Liu, L., Li, H., & Gruteser, M. (2019) · The 25th Annual International Conference on Mobile Computing and Networking · doi:10.1145/3300061.3300116 · Cited by 552 · see citing works
DeepWear: Adaptive Local Offloading for On-Wearable Deep Learning
Xu, M., Qian, F., Zhu, M., Huang, F., Pushp, S., & Liu, X. (2020) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2019.2893250 · Cited by 138 · see citing works
Zhou, Z., Yang, S., Pu, L., & Yu, S. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2984332 · Cited by 77 · see citing works
Self-citationNew Frontiers in IoT: Networking, Systems, Reliability, and Security Challenges
Bagchi, S., Abdelzaher, T. F., Govindan, R., Shenoy, P., Atrey, A., Ghosh, P., & Xu, R. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3007690 · Cited by 72 · see citing works
Real-time Arm Skeleton Tracking and Gesture Inference Tolerant to Missing Wearable Sensors
Liu, Y., Li, Z., Liu, Z., & Wu, K. (2019) · Proceedings of the 17th Annual International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3307334.3326109 · Cited by 71 · see citing works
- Authors
- Liu, S., Lin, Y., Zhou, Z., Nan, K., Liu, H., & Du, J.
- Affiliations
- Xidian University (CN)
- Rice University (US)
- ETH Zurich (CH)
- Venue
- Proceedings of the 16th Annual International Conference on Mobile Systems, Applications, and Services
- Publisher
- ACM
- Published
- 2018-06-10
- Pages
- 389-400
- OpenAlex
- W2860338957
- Cited by
- 217
- References
- 6
- Citations by year
- 2026: 5 · 2025: 13 · 2024: 18 · 2023: 27 · 2022: 45 · 2021: 39 · 2020: 46 · 2019: 22 · 2018: 2
- FWCI
- 8.21
- Type
- conference paper
- Language
- en
- Open access
- Locations
- International Conference on Mobile Systems, Applications, and Services (publishedVersion)
- Singapore Management University Institutional Knowledge (InK) (Singapore Management University) (submittedVersion, other-oa)
- Funders
- National Science Foundation
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Hardware and Architecture › Parallel Computing and Optimization Techniques
- Keywords
- deep neural network compression, mobile devices, resource-constrained deployment, latency reduction, energy efficiency, storage reduction, system-level optimization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
