The DOI matches its Crossref record; 33 of the 36 references it cites were found in a registry or an index.
Neural Networks Meet Physical Networks: Distributed Inference Between Edge Devices and the Cloud
Abstract
We believe that most future video uploaded over the network will be consumed by machines for sensing tasks such as automated surveillance and mapping rather than for human consumption. Today's systems typically collect raw data from distributed sensors, such as drones, with the computer vision logic implemented in the cloud using deep neural networks (DNNs). They use standard video encoding techniques, send it over the network, and then decompress it at the cloud before using the vision DNN. In other words, data encoding and distribution is decoupled from the sensing goal. This is bandwidth inefficient because video encoding schemes, such as MPEG4, might send data tailored for human perception but irrelevant for the overall sensing goal. We argue that data collection and distribution mechanisms should be co-designed with the eventual sensing objective. Specifically, we propose a distributed DNN architecture that learns end-to-end how to represent the raw sensor data and send it over the network such that it meets the eventual sensing task's needs. Such a design naturally adapts to varying network bandwidths between the sensors and the cloud, as well as automatically sends task-appropriate data features.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
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?
In the citing paper
“The vertical model splitting is known to impose a lower data transfer overhead than an alternative method, known as horizontal splitting [138].”
From Confidential Computing Across Edge‐To‐Cloud for Machine Learning: A Survey Study (2025) · cites this paper as [138]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 3×
“This model can be supplied and get periodic cloud software (S/W) updates from an external service, such as image-classification neural networks like GoogleNet[25] and ResNet[7] or Cartographer[8] for map-making in robotics.”
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
(2014) · Cited by 33,419
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225 · cited 1×
“Deep reinforcement learning (deep RL) [19, 22, 24, 26] approximates the solution to an MDP by representing a control policy at = π (st ) with a DNN whose parameters θ are optimized through simulations.”
Reinforcement Learning: An Introduction
(2005) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2004.842673 · Cited by 24,496
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015 · cited 2×
“Though a growing body of research has addressed DNN model compression, the works typically assume compressed models run on a single physical device [5, 6, 9, 15].”
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 · cited 1×
“Deep reinforcement learning (deep RL) [19, 22, 24, 26] approximates the solution to an MDP by representing a control policy at = π (st ) with a DNN whose parameters θ are optimized through simulations.”
Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.03044 · Cited by 8,248
(2010) · Journal of Machine Learning Research · doi:10.5555/1756006.1953039 · Cited by 4,051 · cited 1×
“We also propose using autoencoder NNs, which learn how to best encode and decode information to minimize reconstruction error [3, 28].”
Research works printed but not linked: 8
- Bellman R., 1957, DTIC Document
- S. Han H. Mao and W. J. Dally. Deep compression: Compressing deep neural networks with pruning trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 2015. S. Han H. Mao and W. J. Dally. Deep compression: Compressing deep neural networks with pruning trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 2015. · arXiv
- Jiang A. H., 2018, 2018 USENIX Annual Technical Conference (USENIX ATC 18), 29
- LeCun Y., 1990, Advances in neural information processing systems, 598
- Silver D., 2014, Proceedings of the 31st International Conference on Machine Learning (ICML-14), pages 387--395. JMLR Workshop and Conference Proceedings
- 10.5555/2627435.2670313 · doi:10.5555/2627435.2670313
- 10.2200/S00268ED1V01Y201005AIM009 · doi:10.2200/s00268ed1v01y201005aim009
- Xu K., 2015, International conference on machine learning, 2048
Cited by
Communication-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
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
“robotics-based vision applications [47]–[49].”
Reducto: On-Camera Filtering for Resource-Efficient Real-Time Video Analytics
Li, Y., Padmanabhan, A., Zhao, P., Wang, Y., Xu, G. H., & Netravali, R. (2020) · Proceedings of the Annual conference of the ACM Special Interest Group on Data Communication on the applications, technologies, architectures, and protocols for computer communication · doi:10.1145/3387514.3405874 · Cited by 269
Server-Driven Video Streaming for Deep Learning Inference
Du, K., Pervaiz, A., Yuan, X., Chowdhery, A., Zhang, Q., Hoffmann, H., & Jiang, J. (2020) · Proceedings of the Annual conference of the ACM Special Interest Group on Data Communication on the applications, technologies, architectures, and protocols for computer communication · doi:10.1145/3387514.3405887 · Cited by 243
Do Switches Dream of Machine Learning?: Toward In-Network Classification
Xiong, Z., & Zilberman, N. (2019) · Proceedings of the 18th ACM Workshop on Hot Topics in Networks · doi:10.1145/3365609.3365864 · Cited by 198
Metadata
- Authors
- Chinchali, S. P., Cidon, E., Pergament, E., Chu, T., & Katti, S.
- Affiliations
- Stanford University (US)
- Uhana, Inc.
- Venue
- Proceedings of the 17th ACM Workshop on Hot Topics in Networks
- Publisher
- ACM
- Published
- 2018-11-15
- Pages
- 50-56
- OpenAlex
- W2901502597
- Cited by
- 46
- References
- 36
- Citations by year
- 2025: 5 · 2024: 4 · 2023: 5 · 2022: 4 · 2021: 15 · 2020: 9 · 2019: 4
- FWCI
- 5.35
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM Workshop on Hot Topics in Networks (HotNets) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Signal Processing › Video Coding and Compression Technologies
- 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
- Keywords
- artificial neural networks, physical networks, video compression, spectral efficiency, distributed sensing, unmanned aerial vehicles, automated surveillance, mapping, cloud computing, deep neural network, human perception
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Neural Networks Meet Physical Networks: Distributed Inference Between Edge Devices and the Cloud. https://app.cochat.ai/papers/10.1145/3286062.3286070
- The paper
- Chinchali, S. P., Cidon, E., Pergament, E., Chu, T., & Katti, S. (2018). Neural Networks Meet Physical Networks: Distributed Inference Between Edge Devices and the Cloud. Proceedings of the 17th ACM Workshop on Hot Topics in Networks. https://doi.org/10.1145/3286062.3286070
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.