FastDeepIoT: Towards Understanding and Optimizing Neural Network Execution Time on Mobile and Embedded Devices
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
Deep neural networks show great potential as solutions to many sensing application problems, but their excessive resource demand slows down execution time, pausing a serious impediment to deployment on low-end devices. To address this challenge, recent literature focused on compressing neural network size to improve performance. We show that changing neural network size does not proportionally affect performance attributes of interest, such as execution time. Rather, extreme run-time nonlinearities exist over the network configuration space. Hence, we propose a novel framework, called FastDeepIoT, that uncovers the non-linear relation between neural network structure and execution time, then exploits that understanding to find network configurations that significantly improve the trade-off between execution time and accuracy on mobile and embedded devices. FastDeepIoT makes two key contributions. First, FastDeepIoT automatically learns an accurate and highly interpretable execution time model for deep neural networks on the target device. This is done without prior knowledge of either the hardware specifications or the detailed implementation of the used deep learning library. Second, FastDeepIoT informs a compression algorithm how to minimize execution time on the profiled device without impacting accuracy. We evaluate FastDeepIoT using three different sensing-related tasks on two mobile devices: Nexus 5 and Galaxy Nexus. FastDeepIoT further reduces the neural network execution time by 48% to 78% and energy consumption by 37% to 69% compared with the state-of-the-art compression algorithms.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Classification And Regression Trees
Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (2017) · doi:10.1201/9781315139470 · Cited by 11,417
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Zhang, X., Zhou, X., Lin, M., & Sun, J. (2017) · arXiv · doi:10.48550/arxiv.1707.01083 · Cited by 9,982
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
Zhang, X., Zhou, X., Lin, M., & Sun, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00716 · Cited by 9,982
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Iandola, F. N., Han, S., Moskewicz, M. W., Ashraf, K., Dally, W. J., & Keutzer, K. (2016) · arXiv · doi:10.48550/arxiv.1602.07360 · Cited by 6,201 · cited 2×
“Most manually designed time-efficient neural network structures for mobile devices use parameter size or FLOPs as the indicator of execution time [15, 16, 40].”
BackgroundMethodHan, S., Mao, H., & Dally, W. J. (2015) · arXiv · doi:10.48550/arxiv.1510.00149 · Cited by 4,662
Stisen, A., Blunck, H., Bhattacharya, S., Prentow, T. S., Kjærgaard, M. B., Dey, A., Sonne, T., & Jensen, M. M. (2015) · Proceedings of the 13th ACM Conference on Embedded Networked Sensor Systems · doi:10.1145/2809695.2809718 · Cited by 714 · cited 1×
“ivity recognition (HHAR). This task focuses on the generalization ability with human who has not appeared in the training dataset. During this experiment, we use the dataset collected by Allan et al. [30]. During this evaluation, we use DeepSense structure as the original network structure [34]. Table 8 illustrates Se…”
MethodDeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing
Yao, S., Hu, S., Zhao, Y., Zhang, A., & Abdelzaher, T. (2017) · Proceedings of the 26th International Conference on World Wide Web · doi:10.1145/3038912.3052577 · Cited by 667 · cited 2×
“k models are especially good at fusing multiple sensing modalities and extracting temporal relationships, which have shown remarkable improvements in audio sensing [11, 17], tracking and localization [34], human activity recognition [24, 34, 36], and environment sensing [35]. Applying deep neural networks to mobile an…”
BackgroundMethodSelf-citationMultimodal Deep Learning for Activity and Context Recognition
Radu, V., Tong, C., Bhattacharya, S., Lane, N. D., Mascolo, C., Marina, M. K., & Kawsar, F. (2018) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3161174 · Cited by 281 · cited 1×
“Neural network models are especially good at fusing multiple sensing modalities and extracting temporal relationships, which have shown remarkable improvements in audio sensing [11, 17], tracking and localization [34], human activity recognition [24, 34, 36], and environment sensing [35].”
BackgroundBhattacharya, S., & Lane, N. D. (2016) · Proceedings of the 14th ACM Conference on Embedded Networked Sensor Systems CD-ROM · doi:10.1145/2994551.2994564 · Cited by 236
Yao, S., Zhao, Y., Zhang, A., Su, L., & Abdelzaher, T. (2017) · Proceedings of the 15th ACM Conference on Embedded Network Sensor Systems · doi:10.1145/3131672.3131675 · Cited by 188
Self-citationDoppleSleep: a contactless unobtrusive sleep sensing system using short-range Doppler radar
Rahman, T., Adams, A. T., Ravichandran, R. V., Zhang, M., Patel, S. N., Kientz, J. A., & Choudhury, T. (2015) · Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing · doi:10.1145/2750858.2804280 · Cited by 175 · cited 1×
“114.9 CNN2 32 8 452.4 M 300.2 CNN3 66 32 3732.3 M 908.3 CNN4 43 64 4863.3 M 751.7 smarter and more user-friendly sensing applications in several embedded systems areas, including health and wellness [6, 25, 29, 33], context sensing [7, 21, 23, 31, 39], and object detection and localization [9, 14, 18, 19, 22, 32]. At…”
BackgroundInfluentialGeorgiev, P., Bhattacharya, S., Lane, N. D., & Mascolo, C. (2017) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3131895 · Cited by 67 · cited 1×
“ges, speech and audio. Neural network models are especially good at fusing multiple sensing modalities and extracting temporal relationships, which have shown remarkable improvements in audio sensing [11, 17], tracking and localization [34], human activity recognition [24, 34, 36], and environment sensing [35]. Applyi…”
Background
Cited by
Deep Learning in Mobile and Wireless Networking: A Survey
Zhang, C., Patras, P., & Haddadi, H. (2019) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2019.2904897 · Cited by 1,768
Zeng, L., Chen, X., Zhou, Z., Yang, L., & Zhang, J. (2021) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2020.3042320 · Cited by 313
Machine Learning/Artificial Intelligence for Sensor Data Fusion–Opportunities and Challenges
Blasch, E., Pham, T., Chong, C.-Y., Koch, W., Leung, H., Braines, D., & Abdelzaher, T. (2021) · IEEE Aerospace and Electronic Systems Magazine · doi:10.1109/maes.2020.3049030 · Cited by 207
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
“For example, rather than minimizing computational cost, a model that fully utilizes an available GPU will give a better quality/consumption trade-off [129].”
BackgroundSelf-citationYao, S., Zhao, Y., Shao, H., Liu, D., Liu, S., Hao, Y., Piao, A., Hu, S., Lu, S., & Abdelzaher, T. F. (2019) · IEEE INFOCOM 2019 - IEEE Conference on Computer Communications · doi:10.1109/infocom.2019.8737500 · Cited by 52
Self-citation
Metadata
- Authors
- Yao, S., Zhao, Y., Shao, H., Liu, S., Liu, D., Su, L., & Abdelzaher, T.
- Venue
- Proceedings of the 16th ACM Conference on Embedded Networked Sensor Systems
- Publisher
- ACM
- Published
- 2018-11-04
- Pages
- 278-291
- OpenAlex
- W4289305285
- Cited by
- 146
- References
- 14
- FWCI
- 5.46
- Type
- conference paper
- Language
- en
- Open access
- green
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.