Edge-Host Partitioning of Deep Neural Networks with Feature Space Encoding for Resource-Constrained Internet-of-Things Platforms
Open accessAbstract
This paper introduces partitioning an inference task of a deep neural network between an edge and a host platform in the IoT environment. We present a DNN as an encoding pipeline, and propose to transmit the output feature space of an intermediate layer to the host. Encoding of the feature space is proposed to enhance the maximum input rate supported by the edge platform and/or reduce the energy of the edge platform. Simulation results show that partitioning a DNN coupled with feature space encoding enables significant improvement in the energy-efficiency and throughput over the baseline configurations that perform the entire inference at the edge or at the host.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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?
It is possible to vertically partition an NN model and perform some layers on the trusted machine and process the rest on the untrusted one.
“It is even possible to vertically partition the NN model and perform some layers of it on the trusted machine and process the rest of it on the untrusted one [137].”
From Confidential Computing Across Edge‐To‐Cloud for Machine Learning: A Survey Study (2025) · cites this paper as [137]
The Introduction and Section 3 describe splitting inference at an intermediate layer: the edge processes the earlier layers and the host processes the rest. Our copy does not designate either machine as trusted or untrusted, so it does not support that security characterization. (LLM, conf=0.88)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks
Chen, Y.-H., Krishna, T., Emer, J. S., & Sze, V. (2017) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2016.2616357 · Cited by 3,247 · see citing works
Cross-scene crowd counting via deep convolutional neural networks
Zhang, C., Li, H., Wang, X., & Yang, X. (2015) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2015.7298684 · Cited by 1,155 · see citing works
Distributed Deep Neural Networks Over the Cloud, the Edge and End Devices
Teerapittayanon, S., McDanel, B., & Kung, H. T. (2017) · 2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2017.226 · Cited by 843 · see citing works
Image Quality Assessment Guided Deep Neural Networks TrainingPreprint
Chen, Z., Lin, W., Wang, S., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.03880 · Cited by 10 · see citing works
Flagged first, then by citations
Research works printed but not linked: 4
- [4]4. Song Han et al. Deep Compression -Compressing Deep Neu- ral Networks with Pruning, Trained Quantization and Huffman Coding. ICLR, 2016.
- [11]11. Song Han et al. Eie: Efficient inference engine on compressed deep neural network. In ISCA, ISCA '16, 2016.
- [13]13. Karen Simonyan et al. Very deep convolutional networks for large-scale image recognition. CoRR, 2014.
- [14]14. Songtao Wu et al. Deep residual learning for image recognition. In CVPR, 2017.
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
“[83] propose an edge-host partitioning method, which combines model partition with lossy feature encoding.”
MethodCommunication-efficient edge ai: algorithms and systems
Shi, Y., Yang, K., Jiang, T., Zhang, J., & Letaief, K. B. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.3007787 · Cited by 488 · see citing works
Model inversion attacks against collaborative inference
He, Z., Zhang, T., & Lee, R. B. (2019) · Proceedings of the 35th Annual Computer Security Applications Conference · doi:10.1145/3359789.3359824 · Cited by 313 · see citing works
BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systems
Shao, J., & Zhang, J. (2020) · 2020 IEEE International Conference on Communications Workshops (ICC Workshops) · doi:10.1109/iccworkshops49005.2020.9145068 · Cited by 200 · see citing works
Designing adaptive neural networks for energy-constrained image classification
Stamoulis, D., Chin, T.-W. (., Prakash, A. K., Fang, H., Sajja, S., Bognar, M., & Marculescu, D. (2018) · Proceedings of the International Conference on Computer-Aided Design · doi:10.1145/3240765.3240796 · Cited by 63 · see citing works
Neural Networks Meet Physical Networks: Distributed Inference Between Edge Devices and the Cloud
Chinchali, S. P., Cidon, E., Pergament, E., Chu, T., & Katti, S. (2018) · Proceedings of the 17th ACM Workshop on Hot Topics in Networks · doi:10.1145/3286062.3286070 · Cited by 46 · see citing works
Confidential Computing Across Edge‐To‐Cloud for Machine Learning: A Survey Study
Zobaed, S., & Amini Salehi, M. (2025) · Software Practice and Experience · doi:10.1002/spe.3398 · Cited by 21 · see citing works
- Authors
- Ko, J. H., Na, T., Amir, M. F., & Mukhopadhyay, S.
- Affiliations
- Georgia Institute of Technology (US)
- Venue
- 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
- Publisher
- IEEE
- Published
- 2018-11
- Pages
- 1-6
- OpenAlex
- W2785938317
- Cited by
- 153
- References
- 4
- Citations by year
- 2025: 10 · 2024: 15 · 2023: 36 · 2022: 26 · 2021: 34 · 2020: 18 · 2019: 10 · 2018: 4
- FWCI
- 13.58
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Office of Naval Research
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Hardware and Architecture › Energy Efficiency in Computing
- Keywords
- deep neural network inference, Internet of Things, resource-constrained devices, energy efficiency, throughput, edge computing
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
