Deep Learning With Edge Computing: A Review
The DOI matches its Crossref record; 130 of the 141 references it cites were found in a registry or an index.
Abstract
Deep learning is currently widely used in a variety of applications, including computer vision and natural language processing. End devices, such as smartphones and Internet-of-Things sensors, are generating data that need to be analyzed in real time using deep learning or used to train deep learning models. However, deep learning inference and training require substantial computation resources to run quickly. Edge computing, where a fine mesh of compute nodes are placed close to end devices, is a viable way to meet the high computation and low-latency requirements of deep learning on edge devices and also provides additional benefits in terms of privacy, bandwidth efficiency, and scalability. This paper aims to provide a comprehensive review of the current state of the art at the intersection of deep learning and edge computing. Specifically, it will provide an overview of applications where deep learning is used at the network edge, discuss various approaches for quickly executing deep learning inference across a combination of end devices, edge servers, and the cloud, and describe the methods for training deep learning models across multiple edge devices. It will also discuss open challenges in terms of systems performance, network technologies and management, benchmarks, and privacy. The reader will take away the following concepts from this paper: understanding scenarios where deep learning at the network edge can be useful, understanding common techniques for speeding up deep learning inference and performing distributed training on edge devices, and understanding recent trends and opportunities.
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
“As mentioned in Section 2.1, the progress of DL is very fast but when it comes to application in Edge or IoT devices then a huge gap is noticeable [67].”
From A survey on deep transfer learning to edge computing for mitigating the COVID-19 pandemic (2020) · cites this paper as [67]
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
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
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
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
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
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
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
(2016) · Cited by 31,590
Research works printed but not linked: 30
- Jeans, 2019, Related’s Hudson Yards: Smart City or Surveillance City?
- AT&T Multi-Access Edge Computing
- Blog, Edge Computing at Chick-Fil-A
- Goodfellow, 2016, Deep Learning, 1
- 10.1145/3299710.3211336 · DOI · Paper page
- Tensorflow
- Tensorflowlite
- Caffe2
- Caffe
- Pytorch
- Cuda
- Cudnn
- AWS Deeplens
- Deep Learning for Siri’s Voice: On-Device Deep Mixture Density Networks for Hybrid Unit Selection Synthesis
- Google Duplex: An AI System for Accomplishing Real-World Tasks Over the Phone
- Pagespeed Insights: Improve Server Response Time
- 2017, Hey Siri: An On-Device DNN-Powered Voice Trigger for Apple’s Personal Assistant
- Google’s Pixel Buds are no Match for Professional Interpreters
- Jindal, 2018, Enabling Full Body AR With Mask R-CNN2GO
- 10.1145/3081333.3081360 · DOI · Paper page
- Edge TPU.
- VPU.
- NVIDIA EGX Edge Computing Platform
- Qualcomm Neural Processing SDK for AI
- 10.1109/MNET.2018.1700202 · DOI · Paper page
- Arcore Overview
- Teerapittayanon, 2017, BranchyNet: Fast inference via early exiting from deep neural networks, CoRR, abs/1709.01686, 1 · arXiv
- 10.1145/3195970.3196023 · doi:10.1145/3195970.3196023 · Paper page
- Hsieh, Gaia: Geo-distributed machine learning approaching LAN speeds, 629
- 10.1109/NCA.2017.8171350 · DOI · Paper page
Cited by
Items 801–900 of 1,000
HW-SW Optimization of DNNs for Privacy-Preserving People Counting on Low-Resolution Infrared Arrays
Risso, M., Xie, C., Daghero, F., Burrello, A., Mollaei, S., Castellano, M., Macii, E., Poncino, M., & Pagliari, D. J. (2024) · Design, Automation, and Test in Europe · doi:10.23919/date58400.2024.10546798 · Cited by 7
Yu, P., Zhao, H., Geng, X., Hu, M., Yan, H., Long, D., Guo, H., & Zong, B. (2024) · Alexandria Engineering Journal · doi:10.1016/j.aej.2024.08.105 · Cited by 4
Correlating measures of hierarchical structures in artificial neural networks with their performance
Xu, Z., Zhu, Y., Hong, B., Wu, X., Zhang, J., Cai, M., Zhou, D., & Liu, Y. (2024) · npj Complexity · doi:10.1038/s44260-024-00015-x · Cited by 9
Adaptive ensemble optimization for memory-related hyperparameters in retraining DNN at edge
Xu, Y., Han, R., Zuo, X., Ouyang, J., Liu, C. H., & Chen, L. Y. (2024) · Future Generation Computer Systems · doi:10.1016/j.future.2024.107600 · Cited by 4
Rangsikunpum, A., Amiri, S., & Ost, L. C. (2024) · IET Computers & Digital Techniques · doi:10.1049/cdt2/6214436 · Cited by 4
Akande, A. J., Hóu, Z., Foo, E., & Li, Q. (2025) · Computers & Security · doi:10.1016/j.cose.2025.104455 · Cited by 5
Jiang, Y., Zhao, P. F., Zhao, C., & Lin, J. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130835 · Cited by 6
Task Offloading with Uncertain Processing Cycles
Li, S., Li, C., Huang, Y., Jalaian, B. A., Hou, Y. T., & Lou, W. (2021) · ACM International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc) · doi:10.1145/3466772.3467034 · Cited by 4
Bondarchuk, A. S., Shashev, D., & Shidlovskiy, S. (2021) · Optoelectronics Instrumentation and Data Processing · doi:10.3103/s8756699021020047 · Cited by 4
Kurniawan, I. F., Asyhari, A. T., He, F., & Liu, Y. (2021) · Computer Communications · doi:10.1016/j.comcom.2021.07.020 · Cited by 4
Ensemble Online Sequential Extreme Learning Machine for Air Quality Prediction
Ye, L., Cao, W., Liu, Y., Li, D., & Wang, Q. (2021) · IEEE International Conference on Control Science and Systems Engineering (ICCSSE) · doi:10.1109/iccsse52761.2021.9545089 · Cited by 4
“In recent years, as machine learning technology (especially deep learning) has shown exciting breakthroughs in many fields such as computer vision and natural language processing [1][2], researchers have begun to try to build air quality prediction systems based on related technologies.”
BackgroundDevelopment of a micro weather station using Arduino and Internet of Things
Essiane, S. N., & Essama, B. G. O. (2021) · Physics Education · doi:10.1088/1361-6552/ac2670 · Cited by 4
Placement of DNN Models on Mobile Edge Devices for Effective Video Analysis
Constantinou, G., Shahabi, C., & Kim, S. H. (2021) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata52589.2021.9671866 · Cited by 4
(2021) · Global NEST Journal · doi:10.30955/gnj.003923 · Cited by 4
Energy and Cost Considerations for GPU Accelerated AI Inference Workloads
Molom-Ochir, T., & Shenoy, R. (2021) · IEEE MIT Undergraduate Research Technology Conference (URTC) · doi:10.1109/urtc54388.2021.9701614 · Cited by 5
Image Classification for Edge-Cloud Setting: A Comparison Study for OCR Application
Tan, K. K. H., Wong, Y. W., & Nugroho, H. (2022) · Pertanika journal of science & technology · doi:10.47836/pjst.30.2.17 · Cited by 4
Clustering-Based Decision Tree for Vehicle Routing Spatio-Temporal Selection
Liu, Y., Zhang, L., Zhou, Y., Xu, Q., Fu, W., & Shen, T. (2022) · Electronics · doi:10.3390/electronics11152379 · Cited by 4
Castilla-Arquillo, R., Pérez-del-Pulgar, C. J., Paz-Delgado, G. J., & Gerdes, L. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3219306 · Cited by 4
“An alternative is to complement these resource-constrained embedded processors with FPGA-based DNN accelerators and/or custom, energy efficient Application Specific Integrated Circuits (ASICs) [16].”
MethodRETRACTED ARTICLE: Collaborative offloading decision policy framework in IoT using edge computing
Shirke, A., & Chandane, M. M. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14383-4 · Cited by 4
“There are different frameworks and architectures are available to different issues associated with offloading [12, 25, 26].”
RetractedAn ENet Semantic Segmentation Method Combined with Attention Mechanism
Bai, W. (2023) · Computational Intelligence and Neuroscience · doi:10.1155/2023/6965259 · Cited by 5
Performance trade offs in IoT-based traffic monitoring and incident detection systems
Ducca, S. V., & Margi, C. B. (2022) · Symposium on Internet of Things (SIoT) · doi:10.1109/siot56383.2022.10070171 · Cited by 4
“The data can either be relayed to be processed in the cloud, which could cause problems due to increased latency and constant need for internet connection [6], or be handled by edge computing, using a local mesh of computing nodes closer to the sensors, which could increase infrastructure complexity and cost but impro…”
Flex-SNN: Spiking Neural Network on Flexible Substrate
Oshima, K., Kuribara, K., & Sato, T. G. (2023) · IEEE Sensors Letters · doi:10.1109/lsens.2023.3271988 · Cited by 5
“Edge computing in sensor systems, which involves low-power on-chip computing for real-time signal processing and communication cost reduction, has gained considerable attention [6], [7], [8].”
BackgroundDeep Learning for IoT “Artificial Intelligence of Things (AIoT)”
Mohamed, K. S. (2023) · Synthesis lectures on engineering, science, and technology · doi:10.1007/978-3-031-35737-4_3 · Cited by 6
Machine Learning - Imaging Applications in Transport Systems: A Review
Adams, A. J., Abu-Mahfouz, A. M. I., & Hancke, G. P. (2023) · International Conference on Electrical, Computer and Energy Technologies (ICECET) · doi:10.1109/icecet58911.2023.10389341 · Cited by 4
“To ensure large scale adoption, deploying machine learning vision models (based on deep learning) on cost effective and suitable edge devices [4] is needed.”
MethodAhmed, M. S., & Giordano, S. (2023) · Globecom · doi:10.1109/globecom54140.2023.10437676 · Cited by 4
“From computer vision tasks, such as object detection on cameras, to natural language processing applications generating text on smartphones, and data analytic applications detecting anomalies on sensors or IoT devices, deep learning has showcased its significant potential in edge computing [1].”
BackgroundA Converting Autoencoder Toward Low-latency and Energy-efficient DNN Inference at the Edge
Mahmud, H., Kang, P., Desai, K., Lama, P., & Prasad, S. K. (2024) · IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum · doi:10.1109/ipdpsw63119.2024.00117 · Cited by 4
“These issues are becoming more prominent for deep learning at the edge [3], [25].”
BackgroundPerspectives, Challenges, and the Future of Biomedical Technology and Artificial Intelligence
Tovar‐Arriaga, S., Perez-Soto, G. I., Camarillo-Gómez, K. A., Avilés, M., & Rodríguez‐Reséndiz, J. (2024) · Technologies · doi:10.3390/technologies12110212 · Cited by 4
A Multi-Agent Approach for Vehicle-to-Fog Fair Computation Offloading
Strugeon, E. G.-L., Ouarnoughi, H., & Niar, S. (2020) · IEEE/ACS International Conference on Computer Systems and Applications (AICCSA) · doi:10.1109/aiccsa50499.2020.9316512 · Cited by 5
“Among the greedy embedded applications, AI applications for instance, and especially those based on deep learning models, can be executed: 1) on edge devices, 2) on fog or cloud servers, or 3) across these different levels [13].”
BackgroundTransfer Learning on the Edge Networks
Saggu, D., & Azim, A. (2021) · IEEE International Systems Conference (SysCon) · doi:10.1109/syscon48628.2021.9447110 · Cited by 4
“In [7], they discussed interfering with various computer nodes with network edge to find out some new approaches for the quick execution of the algorithms.”
BackgroundKubernetes-based DL Offloading Framework for Optimizing GPU Utilization in Edge Computing
Kim, C., Kim, R., Kim, G.-Y., & Kim, S. (2021) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc52510.2021.9621002 · Cited by 4
On the impact of smart sensor approximations on the accuracy of machine learning tasks
Pagliari, D. J., & Poncino, M. (2020) · Heliyon · doi:10.1016/j.heliyon.2020.e05750 · Cited by 5
“in the computations performed while running a classification [2, 3].”
BackgroundMethodMorabito, R., & Chiang, M. (2021) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs51616.2021.00115 · Cited by 4
Commentary: Leveraging Edge Computing Technology for Digital Pathology
Yousif, M. Q., Balis, U. J., Parwani, A. V., & Pantanowitz, L. (2021) · Journal of Pathology Informatics · doi:10.4103/jpi.jpi_112_20 · Cited by 4
“Contrary to other available telepathology solutions, by employing edge computing, their system integrates an image processing algorithm together with high‐speed data transfer with a latency on the order of hundreds of milliseconds.[2] In addition to allowing remote control of microscopic images, this innovative system…”
MethodPost-hoc Models for Performance Estimation of Machine Learning InferencePreprint
Zhang, X., Oymak, S., & Chen, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.02459 · Cited by 8
Self-citationRosa, G. L. D. M., Mohanram, P., Gilerson, A., & Schmitt, R. H. (2023) · Preprints.org · doi:10.20944/preprints202305.1563.v1 · Cited by 5
Paripati, L. K., & Hajari, V. R. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5052124 · Cited by 4
Li, P. (2024) · Entertainment Computing · doi:10.1016/j.entcom.2024.100781 · Cited by 3
On the Robustness of Compressed Models with Class Imbalance
Ali, B. S., Sarhan, N. J., & Alawad, M. (2024) · Computers · doi:10.3390/computers13110297 · Cited by 3
Al-rubaye, M., & Aral, A. (2025) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-031-87778-0_27 · Cited by 3
Zeng, Y., Liu, A., Huang, S., Chen, X., Liang, W., & Zhou, X. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3584811 · Cited by 4
Zhao, R., Luo, C., Zhang, Q., Wei, Q., Zhang, X., Wang, M., Zhang, J., & Li, H. (2025) · Smart Agricultural Technology · doi:10.1016/j.atech.2025.101330 · Cited by 6
Over-the-Air Inference Through Analog Computation Over Multi-Hop MIMO Networks
Bian, C., Hua, M., & Gündüz, D. (2025) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2025.3602209 · Cited by 8
“This is because the standard network does not take the Frobenius norms of W i , i ∈ [1 , N ] , into account.”
Individual plant detection and tracking for agricultural robotics in precision field management
Gao, R., Sun, Y., Chen, Y., Jiang, H., Wang, D., Ning, T., Wang, K., & Qiao, Y. (2025) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2025.111063 · Cited by 3
Joint Optimization of Sampling and Model Partitioning for AoI-Centric Edge Intelligence
Zou, Y., Wang, J., Gan, Z., Zhou, J., Sun, J., & Zhang, Y. (2025) · Tsinghua Science & Technology · doi:10.26599/tst.2025.9010019 · Cited by 3
HTCNN: High-Throughput Batch CNN Inference With Homomorphic Encryption
Ye, Z., Wang, T., Huang, T., Li, Y., Wang, C., Cheung, R. C. C., & Huang, K. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3627562 · Cited by 3
“However,anefficientsolution forprocessingamoderateandvariablenumberofinputswithfasthomomorphicinferencecapabilitiesonresource-constrained platforms[18],[19]isstilllacking.”
Yu, M., Chen, W., & Hou, J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130204 · Cited by 9
Survey on Applications, Techniques and Challenges of Machine Learning for Edge Environments
Rajassekharan, D. (2025) · Journal of Soft Computing Paradigm · doi:10.36548/jscp.2025.4.002 · Cited by 3
Online training and pruning of multi‐wavelength photonic neural networks
Zhang, J., Zhang, W., Xu, T., Xu, L., Doris, E. A., Shastri, B. J., Huang, C., & Prucnal, P. R. (2025) · Nanophotonics · doi:10.1515/nanoph-2025-0296 · Cited by 4
Xin, J., Li, X., Kilper, D. C., & Huang, S. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3637030 · Cited by 6
“With the simulated metro network topology unchanged, 12 and 16 edge servers are deployed at [1,3,5,17,19,27,28,32,9,14,22,30] and [1,3,5,17,19,27,28,32,9,14,22,30,10,12,15,20], respectively.”
Zhang, G., & Ru, Y. (2025) · Applied Sciences · doi:10.3390/app16010352 · Cited by 3
Implementing Neural Networks Over-the-Air via Reconfigurable Intelligent Surfaces
Hua, M., Bian, C., Wu, H., & Gündüz, D. (2026) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2026.3660908 · Cited by 15
“In this paper, we investigate reconfigurable intelligent surface (RIS)-aided multiple-input-multiple-output (MIMO) OAC systems designed to emulate the fully-connected (FC) layer of a neural network (NN) via analog OAC, where the RIS and the transceivers are jointly adjusted to engineer the ambient…”
Khan, T. M., Haq, Q. E. U., Iqbal, S., & Soomro, T. A. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114526 · Cited by 8
Multi-view Representation Learning with Deep Features for Offline Signature Verification
Zhao, X., Liu, C., Zhang, B., Yuan, L., & Zheng, Y. (2021) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-92638-0_16 · Cited by 3
Lightweight CNN-Based Deep Neural Networks Application in Safety Measurement
Lua, W. K. H., Yau, P. C., Seow, C. K., & Wong, D. (2022) · International Conference on Pattern Recognition and Artificial Intelligence (PRAI) · doi:10.1109/prai55851.2022.9904161 · Cited by 3
“Deep learning for Edge Computing and IoT architectures has shown to be effective in reducing data processing requirements and relieving the pressure of the cloud [17, 18].”
BackgroundAutomatic Detection of People Getting Into a Bus in a SMART Public Transportation System
Alizadeh, R., Savaria, Y., & Nerguizian, C. (2022) · IEEE International Conference on Electronics, Circuits and Systems (ICECS) · doi:10.1109/icecs202256217.2022.9971097 · Cited by 3
“The benefits of using edge computing and compute nodes close to the edge is that it allows reducing processing latency [4].”
BackgroundDetection Method of River Floating Objects based on Edge Computing
Li, H., Jia, H., Zhang, R., Yang, S., Qi, Q., & Liu, T. (2023) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2456/1/012035 · Cited by 3
“The video processing flow based on edge computing [8] is shown in Figure 1.”
MethodHe, S., Zhang, H., Li, M., Zhu, H., Chen, C., Liu, Q., & Zeng, X. (2023) · IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS) · doi:10.1109/aicas57966.2023.10168618 · Cited by 3
“Recently, deep learning processors targeted on edge devices have been proposed to protect personal privacy and reduce communication latency [2].”
BackgroundAdvancements and Challenges in Deep Learning-Driven Marine Data Assimilation: A Comprehensive Review
Ma, Y., Zhang, D., Zhang, Y., Zhao, G., Xie, Y., & Jiang, H. (2023) · COMPUTATIONAL RESEARCH PROGRESS IN APPLIED SCIENCE & ENGINEERING · doi:10.61186/crpase.9.4.2876 · Cited by 3
Lightweight Multimodal Fusion Computing Model for Emotional Streaming in Edge Platform
Karjee, J., Kakwani, K., Anand, K., & Praveen Naik, S. (2024) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc51664.2024.10454758 · Cited by 3
“Another study [8] suggested an edge computing solution incorporating a deep learning algorithm to enable intelligent data processing at the edge.”
BackgroundMDP: Model Decomposition and Parallelization of Vision Transformer for Distributed Edge Inference
Wang, W., Zhang, Y., Jin, Y., Han, T., & Chen, L. (2023) · International Conference on Mobility, Sensing and Networking (MSN) · doi:10.1109/msn60784.2023.00086 · Cited by 4
“There are two reasons for its rising [5], [6].”
BackgroundChainNet: A Customized Graph Neural Network Model for Loss-Aware Edge AI Service Deployment
Niu, Z., Roveri, M., & Casale, G. (2024) · International Conference on Dependable Systems & Networks/Proceedings · doi:10.1109/dsn58291.2024.00034 · Cited by 6
“Although deploying partitioned DNN models has been a topic of much research [9], existing research assumes that each DNN fragment will operate under a light workload with little resource contention and congestion, resulting in negligible data loss.”
EdgeScan for IoT Contextual Understanding With Edge Computing and Image Captioning
Hafeth, D. A., Al-Khafajiy, M., & Kollias, S. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3492066 · Cited by 5
“Commercial devices, such as Amazon DeepLens [32], [33], also follow an Edge-based approach, where image detection is performed locally in order to reduce latency, and scenes of interest are only uploaded to the cloud for remote viewing if an interesting object is detected, in order to save…”
Power-of-2-Arms for Adversarial Bandit Learning With Switching Costs
Shi, M., Lin, X., & Jiao, L. (2025) · IEEE Transactions on Networking · doi:10.1109/ton.2024.3522073 · Cited by 4
“Consider edge computing with artificial intelligence (Edge AI) [2], [3] as an example, where an edge server close to the end users downloads machine learning (ML) models from the cloud to process incoming inference requests.”
Giacomo, S. D., Ronchi, M., Amadori, M., Borghi, G., Carminati, M., & Fiorini, C. E. (2025) · IEEE Transactions on Radiation and Plasma Medical Sciences · doi:10.1109/trpms.2025.3530774 · Cited by 4
“Edge computing enables a considerable portion of the processing to be offloaded to dedicated hardware at the sensor level, resulting in bene-fits in terms of reduced latency, decreased computational workload, and less stringent energy requirements for data storage and transmission [1].”
CoDANet: Hardware-Aware Neural Architecture Search for Optimized Deep Learning on FPGAs
Zheng, L. X., Wang, B., Liu, S., & Shi, X. (2024) · International Conference on Artificial Intelligence and Automation Control (AIAC) · doi:10.1109/aiac63745.2024.10899512 · Cited by 3
“However, these networks often demand substantial computational and storage resources, posing significant challenges for deployment on resource-constrained hardware platforms [3].”
Multi-Objective Reverse Offloading in Edge Computing for AI Tasks
Amanatidis, P., Michailidis, G., Karampatzakis, D., Kalenteridis, V., Iosifidis, G., & Λάγκας, Θ. (2025) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2025.3555947 · Cited by 4
“Pre-trained Deep Neural Networks (DNNs) are deployed on the end nodes in large numbers thanks to improvements in end nodes’ hardware and the creation of DNN models that require less processing power and storage at the expense of lower inference accuracy [4], [5], [6].”
RankMap: Priority-Aware Multi-DNN Manager for Heterogeneous Embedded Devices
Καρατζάς, Α., Stamoulis, D. S., & Anagnostopoulos, I. (2025) · Design, Automation, and Test in Europe · doi:10.23919/date64628.2025.10992856 · Cited by 3
“…of Large Language Models (LLMs) and Generative AI, vision models: ( i ) remain more prevalent in edge environments over natural language ones [6], ( ii ) are typically executed on edge hardware more efficiently [7], as ( iii ) major hardware providers like ARM and NVIDIA offer more robust…”
Attention-Driven AI Model Generalization for Workload Forecasting in the Compute Continuum
Gort, B. J. D., Kibalya, G., & Antonopoulos, A. (2025) · IEEE Transactions on Machine Learning in Communications and Networking · doi:10.1109/tmlcn.2025.3584009 · Cited by 5
“A promising strategy involves adopting a centralized ‘‘foundational model’’ architecture, where OmniFORE operates primarily on cloud infrastructure and serves predictions to edge devices through lightweight API calls [56], [62].”
Kwon, J.-W., Anwar, R., & Kim, W.-T. (2025) · Applied Sciences · doi:10.3390/app15147738 · Cited by 3
Yin, J., Wang, B., Wang, T., & Tang, Z. (2025) · Fundamental Research · doi:10.1016/j.fmre.2025.09.014 · Cited by 4
“When combined with AI, edge computing opens up new opportunities for intelligent systems capable of adapting and responding instantly to monitoring demands [ 204 , 205 ].”
Kelle: Co-design KV Caching and eDRAM for Efficient LLM Serving in Edge Computing
Xia, T., & Zhang, S. Q. (2025) · Proceedings of the 58th IEEE/ACM International Symposium on Microarchitecture · doi:10.1145/3725843.3756071 · Cited by 3
“However, edge devices have limited area and power budgets, and expanding SRAM reduces the resources available for other critical components, such as computational cores [14, 39, 79].”
AS-ASR: A Lightweight Framework for Aphasia-Specific Automatic Speech Recognition
Bao, C., Huo, C., Chen, Q., & Gao, C. (2025) · IEEE Biomedical Circuits and Systems Conference (BioCAS) · doi:10.1109/biocas67066.2025.00027 · Cited by 3
“Edge devices offer several advantages, including low power consumption, portability, cost efficiency, and improved data privacy [7].”
Ruan, L., Guo, S., Qiu, X., & Buyya, R. (2021) · CRC Press eBooks · doi:10.1201/9780367423926-2 · Cited by 3
Data-Driven Predictive Maintenance: A Methodology Primer
Cerquitelli, T., Nikolakis, N., Morra, L., Bellagarda, A., Orlando, M., Salokangas, R., Saarela, O., Hietala, J., Kaarmila, P., & Macii, E. (2021) · Information fusion and data science · doi:10.1007/978-981-16-2940-2_3 · Cited by 5
No Free Lunch: Balancing Learning and Exploitation at the Network Edge
Mason, F., Chiariotti, F., & Zanella, A. (2022) · International Conference on Communications · doi:10.1109/icc45855.2022.9838277 · Cited by 4
A multi‐step finite‐state automaton for arbitrarily deterministic Tsetlin Machine learning
Abeyrathna, K. D., Granmo, O., Shafik, R., Jiao, L., Wheeldon, A., Yakovlev, A., Lei, J., & Goodwin, M. (2021) · Expert Systems · doi:10.1111/exsy.12836 · Cited by 3
Farhan, S., Jha, U., Rawat, R., & Govindaraju, M. (2021) · IEEE International Conference on Electronics, Circuits and Systems (ICECS) · doi:10.1109/icecs53924.2021.9665474 · Cited by 5
Visual AI Applications on Smart Delivery Units
Schoepflin, D., Ünal, Ö. A., Scheffler, P., Wendt, A., Gomse, M., & Schüppstuhl, T. (2021) · IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT) · doi:10.1109/gcaiot53516.2021.9693060 · Cited by 3
Automated Deep Learning for Medical Imaging
O’Byrne, C., Raja, L., Struyven, R., Korot, E., & Keane, P. A. (2022) · Springer eBooks · doi:10.1007/978-3-030-64573-1_269 · Cited by 3
Guo, Z., Wang, J., Liu, S., Ren, J., Xu, Y., & Wang, Y. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3154644 · Cited by 3
“Existing training solutions for EDL usually use the same fixed batch size for each training iteration [1].”
BackgroundMethodInfluentialUnsupervised Test-Time Adaptation of Deep Neural Networks at the Edge: A Case Study
Bhardwaj, K., Diffenderfer, J., Kailkhura, B., & Gokhale, M. B. (2022) · Design, Automation, and Test in Europe · doi:10.23919/date54114.2022.9774580 · Cited by 3
Zhao, D., Li, H., Xu, A., & Song, T. (2022) · Frontiers in Psychology · doi:10.3389/fpsyg.2022.843493 · Cited by 9
“It is an individual’s self-discovery, judgment, evaluation, and adjustment of the knowledge processing process. meaningful learning, knowledge system construction, critical thinking, and metacognitive ability (Chen and Ran, 2019).”
BackgroundSymDNN: Simple & Effective Adversarial Robustness for Embedded Systems
Dey, S., Dasgupta, P., & Chakrabarti, P. P. (2022) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00404 · Cited by 3
“Since the past few years, Edge Computing is showing explosive growth [51], with mobile and embedded computer vision being one of the killer apps [2], and CNNs dominating that landscape [13].”
BackgroundApplication of Deep Learning Model Inference with Batch Size Adjustment
Oh, S., Moon, J., & Kum, S. (2022) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc55196.2022.9952641 · Cited by 3
“Recently, lightweight artificial intelligence models and edge computing are attracting a lot of attention, and deep learning-related research is continuing in the embedded environment [1].”
BackgroundTuan, N. A., Xu, R., Moe, S. J. S., & Kim, D. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3285618 · Cited by 3
“In summary, the tradeoff latency-accuracy in deep learning on the edge is an evolving issue that requires careful consideration of the available resources and ongoing optimization to ensure the best possible results [17].”
BackgroundA Robust NFT Assisted Knowledge Distillation Framework for Edge Computing
Wang, N., Sajjanhar, A., Xiang, Y., & Gao, L. (2023) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-33458-0_2 · Cited by 3
AI/ML-Based Object Detection on FPGA SoC
Sruthi, K., & Nandakumar, R. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-99-1699-3_32 · Cited by 4
Bian, C., Yang, S., Xu, Q., & Feng, J. (2023) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2023.3297771 · Cited by 3
“In the future, the proposed method will be deployed on IoT-based edge computing devices [44], [45] to meet the high prediction accuracy and low-latency requirements in millisecond-scale real-time prediction scenarios.”
MethodInternet of Things and Dew Computing-Based System for Smart Agriculture
Bera, S., Dey, T., Ghosh, S., & Mukherjee, A. (2023) · Internet of things · doi:10.1007/978-981-99-4590-0_14 · Cited by 5
Federated Learning in Wireless Networks via Over-the-Air Computations
Öksüz, H. Y., Molinari, F., Sprekeler, H., & Raisch, J. (2023) · IEEE Conference on Decision and Control (CDC) · doi:10.1109/cdc49753.2023.10384001 · Cited by 5
“In a centralized learning approach, all data are collected in a computationally powerful machine, such as a cloud-based unit or a server, on which the model is trained [4].”
MethodEdge Computing for Sustainable Energy Management: An Environmental Aspect
Kanday, R., & Singh, R. (2023) · International Conference on Contemporary Computing and Informatics (IC3I) · doi:10.1109/ic3i59117.2023.10398093 · Cited by 3
“The energy consumption of peer-to-peer distribution relies more on the end-user's premises than that of centralized distribution, according to other studies [22][23].”
ResultShort-Packet Edge Computing Networks With Execution Uncertainty
Lai, X., Wu, T., Pan, C., Mai, L., & Nallanathan, A. (2024) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2024.3373911 · Cited by 3
Enhancing Edge Intelligence with Layer-wise Adaptive Precision and Randomized PCA
Mishra, S. K., C, V. J. D. G., Maddi, P. A., Tanniru, N. M., & Manthena, S. L. P. (2024) · International Conference on Advancements in Smart, Secure and Intelligent Computing (ASSIC) · doi:10.1109/assic60049.2024.10507942 · Cited by 4
“A comprehensive review of deep learning in the context of edge computing [12], aligns with the goals of this research in enhancing edge intelligence.”
BackgroundLi, S., Li, W., Liu, H., & Sun, W. (2024) · Journal of Systems Science and Systems Engineering · doi:10.1007/s11518-024-5604-1 · Cited by 3
“Edge nodes deployed near the end devices can reduce end-to-end latency and achieve real-time services (Chen and Ran 2019).”
Xiu, W., Johar, M. G. M., Alkawaz, M. H., & Bian, C. (2024) · Journal of Computing and Electronic Information Management · doi:10.54097/ceym1sxx · Cited by 3
“For instance, adjacency lists and CSR are superior for graph traversal, while adjacency matrices are more suitable for rapid retrieval.”
BackgroundMethodInfluentialMarisetty, H. V., Fatima, N., Gupta, M., & Saxena, P. (2024) · Internet of Things · doi:10.1016/j.iot.2024.101375 · Cited by 5
Simulating Load Sharing for Resource Constrained Devices
Kolimago, C., Robson, M. P., Olufowobi, H., & Nwafor, E. (2024) · IEEE Access · doi:10.1109/access.2024.3475996 · Cited by 3
Securing Pseudo-Model Parallelism-Based Collaborative DNN Inference for Edge Devices
Adeyemo, A. A., Patel, P., Hasan, S. R., Rahaman, M. A., & Homsi, S. (2024) · IEEE Access · doi:10.1109/access.2024.3477293 · Cited by 6
Mengistu, T. M., Lin, J.-W., Kuo, P.-H., & Kim, T. (2024) · IEEE Access · doi:10.1109/access.2024.3487073 · Cited by 6
Morita, A., & Okuno, H. (2024) · IEICE Transactions on Electronics · doi:10.1587/transele.2024lhp0003 · Cited by 3
“Due to the growing need for intelligent processing at the network edge, research into implementing AI using edge computing is accelerating (see [12] and [13] for overviews).”
Metadata
- Authors
- Chen, J., & Ran, X.
- Affiliations
- University of California, Riverside (US)
- ORCID
- Chen, Jiasi
- Venue
- Proceedings of the IEEE
- Published
- 2019-08
- Volume
- 107
- Issue
- 8
- Pages
- 1655-1674
- ISSN
- 0018-9219 (ISSN-L)
- 1558-2256
- OpenAlex
- W2960833983
- Cited by
- 1,540
- References
- 141
- Citations by year
- 2026: 205 · 2025: 250 · 2024: 270 · 2023: 245 · 2022: 232 · 2021: 218 · 2020: 114 · 2019: 6
- FWCI
- 77.78
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- Proceedings of the IEEE (publishedVersion)
- Funders
- National Science Foundation (CNS-1817216)
- 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 › Information Systems › Internet of Things and AI
- Keywords
- edge computing, deep learning, edge inference, distributed deep learning training, edge servers, cloud-edge collaboration, Internet of Things, low latency, privacy, spectral efficiency
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.