The DOI matches its Crossref record; 54 of the 54 references it cites were found in a registry or an index.
Task-Oriented Communication for Multidevice Cooperative Edge Inference
Open accessAbstract
This paper investigates task-oriented communication for multi-device cooperative edge inference, where a group of distributed low-end edge devices transmit the extracted features of local samples to a powerful edge server for inference. While cooperative edge inference can overcome the limited sensing capability of a single device, it substantially increases the communication overhead and may incur excessive latency. To enable low-latency cooperative inference, we propose a learning-based communication scheme that optimizes local feature extraction and distributed feature encoding in a task-oriented manner, i.e., to remove data redundancy and transmit information that is essential for the downstream inference task rather than reconstructing the data samples at the edge server. Specifically, we leverage Tishby’s information bottleneck (IB) principle (Tishby et al., 2000) to extract the task-relevant feature at each edge device, and adopt the distributed information bottleneck (DIB) framework of Aguerri and Zaidi, 2021, to formalize a single-letter characterization of the optimal rate-relevance tradeoff for distributed feature encoding. To admit flexible control of the communication overhead, we extend the DIB framework to a distributed deterministic information bottleneck (DDIB) objective that explicitly incorporates the representational costs of the encoded features. As the IB-based objectives are computationally prohibitive for high-dimensional data, we adopt variational app…
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
“Furthermore, it has been extended to the cooperative inference scenario with multiple edge devices in [86] based on distributed information bottleneck [236] and distributed source coding theory.”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [86]
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138
Learning Multiple Layers of Features from Tiny Images
Krizhevsky, A. (2024) · doi:10.57702/zp44cu3g · Cited by 23,395
Auto-Encoding Variational Bayes
Kingma, D. P., & Welling, M. (2013) · arXiv · doi:10.48550/arxiv.1312.6114 · Cited by 20,067
Identity mappings in deep residual networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46493-0_38 · Cited by 10,741
Identity Mappings in Deep Residual Networks
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · arXiv · doi:10.48550/arxiv.1603.05027 · Cited by 10,665 · cited 1×
“MNIST CIFAR-10 Tiny-ImageNet WRGBD ModelNet40 NN1 3 FC layers VGG-19 [47] PreActResNet18 [48] 2 Conv layers 1 FC layer VGG-11 [47] NN2 3 FC layers 2 FC layers 2 Conv layers 1 FC layer 1 FC layer 3 FC layers”
BackgroundA unified architecture for natural language processing: deep neural networks with multitask learning
Collobert, R., & Weston, J. (2008) · Proceedings of the 25th international conference on Machine learning - ICML '08 · doi:10.1145/1390156.1390177 · Cited by 5,058
3D ShapeNets: A deep representation for volumetric shapes
Wu, Z., Song, S., Khosla, A., Yu, F., Zhang, L., Tang, X., & Xiao, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298801 · Cited by 4,550 · cited 5×
“We investigate the performance of these two methods on the ModelNet40 dataset.”
MethodInfluentialNoiseless coding of correlated information sources
Slepian, D., & Wolf, J. (1973) · IEEE Transactions on Information Theory · doi:10.1109/tit.1973.1055037 · Cited by 3,952
Variational Inference: A Review for Statisticians
Blei, D. M., Kucukelbir, A., & McAuliffe, J. D. (2017) · Journal of the American Statistical Association · doi:10.1080/01621459.2017.1285773 · Cited by 3,811
Multi-view Convolutional Neural Networks for 3D Shape Recognition
Su, H., Maji, S., Kalogerakis, E., & Learned-Miller, E. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.114 · Cited by 3,480
El Gamal, A., & Kim, Y.-H. (2011) · Cambridge University Press eBooks · doi:10.1017/cbo9781139030687 · Cited by 2,716
The information bottleneck method
Tishby, N., Pereira, F. C., & Bialek, W. (2000) · arXiv · doi:10.48550/arxiv.physics/0004057 · Cited by 2,626
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
Self-citationVariational Inference: A Review for Statisticians
Blei, D. M., Kucukelbir, A., & McAuliffe, J. (2017) · Figshare · doi:10.6084/m9.figshare.5203696 · Cited by 1,919
Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
Bengio, Y., Léonard, N., & Courville, A. (2013) · arXiv · doi:10.48550/arxiv.1308.3432 · Cited by 1,910
A large-scale hierarchical multi-view RGB-D object dataset
Lai, K., Bo, L., Ren, X., & Fox, D. (2011) · 2011 IEEE International Conference on Robotics and Automation · doi:10.1109/icra.2011.5980382 · Cited by 1,316
Badue, C., Guidolini, R., Carneiro, R. V., Azevedo, P., Cardoso, V. B., Forechi, A., Jesus, L., Berriel, R., Paixão, T. M., Mutz, F., et al. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113816 · Cited by 1,209
A Deep Learning-Based Approach to Progressive Vehicle Re-identification for Urban Surveillance
Liu, X., Liu, W., Mei, T., & Ma, H. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46475-6_53 · Cited by 641 · cited 2×
“Related application scenarios include multi-view object detection [27] in security camera systems and vehicle re-identification [16] in urban surveillance.”
BackgroundToward an Intelligent Edge: Wireless Communication Meets Machine Learning
Zhu, G., Liu, D., Du, Y., You, C., Zhang, J., & Huang, K. (2020) · IEEE Communications Magazine · doi:10.1109/mcom.001.1900103 · Cited by 606
Self-citation6G networks: Beyond Shannon towards semantic and goal-oriented communications
Calvanese Strinati, E., & Barbarossa, S. (2021) · Computer Networks · doi:10.1016/j.comnet.2021.107930 · Cited by 525
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
Self-citationLearning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach
Shao, J., Mao, Y., & Zhang, J. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126087 · Cited by 338
Self-citationA Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets
Chrabąszcz, P., Loshchilov, I., & Hutter, F. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.08819 · Cited by 336 · cited 2×
“1) Datasets: In the multi-view image classification task, we select MNIST [41], CIFAR-10 [42], and Tiny ImageNet [43] for experiments.”
MethodDeep Variational Information Bottleneck
Alemi, A. A., Fischer, I., Dillon, J. V., & Murphy, K. P. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.00410 · Cited by 321 · cited 2×
“,K} satisfies the minimality and sufficiency conditions [28], [29] as follows:”
BackgroundMethodBottleNet++: 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 · cited 1×
“To enable low-latency inference, device-edge co-inference stands out as a promising solution [12], [13], [14], which extracts task-relevant features from the raw input data and forwards them to be processed by an edge server.”
BackgroundSelf-citationBottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Services
Eshratifar, A. E., Esmaili, A., & Pedram, M. (2019) · 2019 IEEE/ACM International Symposium on Low Power Electronics and Design (ISLPED) · doi:10.1109/islped.2019.8824955 · Cited by 196
The Information Bottleneck Problem and its Applications in Machine Learning
Goldfeld, Z., & Polyanskiy, Y. (2020) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2020.2991561 · Cited by 165
Deep learning-based strategies for the detection and tracking of drones using several cameras
Unlu, E., Zenou, E., Riviere, N., & Dupouy, P.-E. (2019) · IPSJ Transactions on Computer Vision and Applications · doi:10.1186/s41074-019-0059-x · Cited by 164
The Conditional Entropy Bottleneck
Fischer, I. (2020) · Entropy · doi:10.3390/e22090999 · Cited by 163 · cited 1×
“,K} satisfies the minimality and sufficiency conditions [28], [29] as follows:”
BackgroundCommunication-Computation Trade-off in Resource-Constrained Edge Inference
Shao, J., & Zhang, J. (2020) · IEEE Communications Magazine · doi:10.1109/mcom.001.2000373 · Cited by 162
Self-citationMultiterminal Source Coding Under Logarithmic Loss
Courtade, T. A., & Weissman, T. (2014) · IEEE Transactions on Information Theory · doi:10.1109/tit.2013.2288257 · Cited by 158
The 3GPP NB-IoT system architecture for the Internet of Things
Zayas, A. D., & Merino, P. (2017) · IEEE International Conference on Communications workshops · doi:10.1109/iccw.2017.7962670 · Cited by 135 · cited 1×
“Specifically, if the multi-device cooperative inference system is supported by the 3GPP narrowband Internet of Things (NB-IoT) standard with an 18 KB/s uplink rate [49],”
MethodCollaborative visual SLAM for multiple agents:A brief survey
Zou, D., Tan, P., & Yu, W. (2019) · Virtual Reality & Intelligent Hardware · doi:10.1016/j.vrih.2019.09.002 · Cited by 123
Multi-Robot Collaborative Perception With Graph Neural Networks
Zhou, Y., Xiao, J., Zhou, Y., & Loianno, G. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3141661 · Cited by 121 · cited 1×
“This classic result has recently received renewed attention and led to several works [23], [24], [25], [26] to develop DNNbased distributed feature encoding schemes in task-oriented communication.”
BackgroundDistributed Variational Representation Learning
Aguerri, I. E., & Zaidi, A. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2928806 · Cited by 84
Lossy Compression for Lossless PredictionPreprint
Dubois, Y., Bloem-Reddy, B., Ullrich, K., & Maddison, C. J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.10800 · Cited by 80
On hypercontractivity and a data processing inequality
Anantharam, V., Gohari, A., Kamath, S., & Nair, C. (2014) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit.2014.6875389 · Cited by 67
Successive Refinement of Images with Deep Joint Source-Channel Coding
Kurka, D. B., & Gündüz, D. (2019) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc.2019.8815416 · Cited by 65 · cited 1×
“For this purpose, we propose a VDDIB-SR method that introduces a selective retransmission (SR) mechanism to the VDDIB framework, which performs multiple sequential communication rounds [37] between the edge devices and the edge server.”
MethodBranchy-GNN: A Device-Edge Co-Inference Framework for Efficient Point Cloud Processing
Shao, J., Zhang, H., Mao, Y., & Zhang, J. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414831 · Cited by 63
Self-citationVector Gaussian CEO Problem Under Logarithmic Loss and Applications
Uğur, Y., Aguerri, I. E., & Zaidi, A. (2020) · IEEE Transactions on Information Theory · doi:10.1109/tit.2020.2972348 · Cited by 57
Predictive View Generation to Enable Mobile 360-degree and VR Experiences
Hou, X., Dey, S., Zhang, J., & Budagavi, M. (2018) · doi:10.1145/3229625.3229629 · Cited by 49
Self-citationLearning to Stop While Learning to PredictPreprint
Chen, X., Dai, H., Li, Y., Gao, X., & Song, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.05082 · Cited by 49
Neural Distributed Source Coding
Whang, J., Nagle, A., Acharya, A., Kim, H., & Dimakis, A. G. (2024) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2024.3412976 · Cited by 38 · cited 1×
“We follow the method in [44] to generate two views for each image by splitting it vertically.”
MethodEnomoro, S., & Eda, T. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i8.16900 · Cited by 30
On Distributed Quantization for Classification
Hanna, O. A., Ezzeldin, Y. H., Sadjadpour, T., Fragouli, C., & Diggavi, S. N. (2020) · IEEE Journal on Selected Areas in Information Theory · doi:10.1109/jsait.2020.2986467 · Cited by 24
Context-Aware Convolutional Neural Network over Distributed System in Collaborative Computing
Choi, J., Hakimi, Z., Shin, P. W., Sampson, J., & Narayanan, V. (2019) · ACM/IEEE Design Automation Conference (DAC) · doi:10.1145/3316781.3317792 · Cited by 20 · cited 4×
“This classic result has recently received renewed attention and led to several works [23], [24], [25], [26] to develop DNNbased distributed feature encoding schemes in task-oriented communication.”
BackgroundMethodInfluentialCommunication-efficient View-Pooling for Distributed Multi-View Neural Networks
Singhal, M., Raghunathan, V., & Raghunathan, A. (2020) · Design, Automation, and Test in Europe · doi:10.23919/date48585.2020.9116528 · Cited by 15
In-network Learning for Distributed Training and Inference in Networks
Moldoveanu, M., & Zaidi, A. (2021) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps52748.2021.9682062 · Cited by 15
On In-network learning. A Comparative Study with Federated and Split Learning
Moldoveanu, M., & Zaidi, A. (2021) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc51858.2021.9593182 · Cited by 13
Neural Distributed Source CodingPreprint
Whang, J., Nagle, A., Acharya, A., Kim, H., & Dimakis, A. G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.02797 · Cited by 10 · cited 1×
“We follow the method in [44] to generate two views for each image by splitting it vertically.”
MethodWireless Image Retrieval at the Edge
Jankowski, M., Gunduz, D., & Mikolajczyk, K. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2020.3036955 · Cited by 3
Enomoto, S., & Eda, T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.09286 · Cited by 3
Cited by
Edge artificial intelligence for 6g: vision, enabling technologies, and applications
Letaief, K. B., Shi, Y., Lu, J., & Lu, J. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126076 · Cited by 829
“Furthermore, it has been extended to the cooperative inference scenario with multiple edge devices in [86] based on distributed information bottleneck [236] and distributed source coding theory.”
BackgroundXu, W., Yang, Z., Ng, D. W. K., Levorato, M., Eldar, Y. C., & Debbah, M. (2023) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2023.3239189 · Cited by 660
“in [229], where a group of edge nodes perform the inference task collaboratively with the assistance of an edge server.”
Wang, Y., Su, Z., Guo, S., Dai, M., Luan, T. H., & Liu, Y. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3263909 · Cited by 357
Zhu, G., Lyu, Z., Jiao, X., Liu, P., Chen, M., Xu, J., Cui, S., & Zhang, P. (2023) · Science China Information Sciences · doi:10.1007/s11432-022-3652-2 · Cited by 239
“Considering edge inference with multiple edge devices, a task-oriented JSCC framework was designed in [90], where a group of edge nodes perform the classification task coordinated by an edge server.”
MethodSemantics-Empowered Communications: A Tutorial-Cum-Survey
Lu, Z., Li, R., Lu, K., Chen, X., Hossain, E., Zhao, Z., & Zhang, H. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3333342 · Cited by 178
“In addition, Shao et al. [158] present a selective retransmission-based communication scheme that leverages Tishby’s IB principle [102] for task-relevant feature extraction and capably identify and skip redundant features to avoid compensating for the potential performance loss due to the…”
Background
Metadata
- Authors
- Shao, J., Mao, Y., & Zhang, J.
- Affiliations
- Hong Kong University of Science and Technology (HK)
- Hong Kong Polytechnic University (HK)
- Venue
- IEEE Transactions on Wireless Communications
- Published
- 2023-01
- Volume
- 22
- Issue
- 1
- Pages
- 73-87
- ISSN
- 1536-1276 (ISSN-L)
- 1558-2248
- OpenAlex
- W3197326271
- Cited by
- 209
- References
- 54
- Citations by year
- 2026: 39 · 2025: 64 · 2024: 68 · 2023: 35
- FWCI
- 18.75
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Wireless Communications (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- arXiv (Cornell University)
- Funders
- General Research Fund (15207220)
- Hong Kong Research Grants Council under the Research Impact Fund
- Start-Up Fund of The Hong Kong Polytechnic University (P0038174)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Computer Networks and Communications › Distributed Sensor Networks and Detection Algorithms
- Physical Sciences › Computer Science › Computer Networks and Communications › Cooperative Communication and Network Coding
- Keywords
- task-oriented communication, information bottleneck, feature redundancy reduction, selective retransmission, low-latency communication, variational approximation
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.