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 101–200 of 1,000
Evaluation and Optimization of Distributed Machine Learning Techniques for Internet of Things
Gao, Y., Kim, M., Thapa, C., Abuadbba, A., Zhang, Z., Camtepe, S. A., Kim, H., & Nepal, . (2021) · IEEE Transactions on Computers · doi:10.1109/tc.2021.3135752 · Cited by 103
Custom Hardware Architectures for Deep Learning on Portable Devices: A Review
Zaman, K. S., Reaz, M. B. I., Ali, S. H. M., Bakar, A. A. A., & Chowdhury, M. E. H. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3082304 · Cited by 102
“However, there is an increasing demand to introduce on-chip intelligence into the smart city and Industry 4.0 infrastructure to improve privacy, latency, and communication overheads [13], [14].”
BackgroundInfluentialAutoML for Video Analytics with Edge Computing
Galanopoulos, A., Ayala‐Romero, J. A., Leith, D. J., & Iosifidis, G. (2021) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom42981.2021.9488704 · Cited by 90
“Another large corpus of works take a computation-offloading perspective and handle computing or network resources without considering video analytics (e.g., accuracy) or NN configurations (e.g. NN size); see [6]–[8] and survey [33].”
BackgroundIsmail, A. A., Khalifa, N. E. M., & El-Khoribi, R. A. (2025) · Cluster Computing · doi:10.1007/s10586-024-04893-7 · Cited by 130
“The heavy DNN models can be partitioned (layer-wise or input-wise) and offloaded [11].”
InfluentialPyramid: Enabling Hierarchical Neural Networks with Edge Computing
He, Q., Dong, Z., Chen, F., Deng, S., Liang, W., & Yang, Y. J. (2022) · International World Wide Web Conference (WWW) · doi:10.1145/3485447.3511990 · Cited by 90
“For example, offloading a camera frame to an AWS server and performing a computer vision task take more than 200 milliseconds end-to-end [4].”
MethodAn edge based hybrid intrusion detection framework for mobile edge computing
Singh, A. P., Chatterjee, K., & Satapathy, S. C. (2021) · Complex & Intelligent Systems · doi:10.1007/s40747-021-00498-4 · Cited by 94
“A literature work has been carried out to examine recent findings in the area of IDS solutions in MEC networks [66– 74].”
Multi-exit DNN Inference Acceleration based on Multi-Dimensional Optimization for Edge Intelligence
Dong, F., Wang, H., Shen, D., Huang, Z., He, Q., Zhang, J., Wen, L., & Zhang, T. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3172402 · Cited by 103
“To meet these requirements for AI applications, deep learning with edge computing, also named edge intelligence, has been envisioned as a promising paradigm [4], [5], [6], [7].”
BackgroundYang, H., Cai, J., Liu, C., Ke, R., & Wang, Y. (2023) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2022.103982 · Cited by 104
Analysis of Training Deep Learning Models for PCB Defect Detection
Park, J.-H., Kim, Y.-S., Seo, H., & Cho, Y.-J. (2023) · Sensors · doi:10.3390/s23052766 · Cited by 99
Supervised Compression for Resource-Constrained Edge Computing Systems
Matsubara, Y., Yang, R., Levorato, M., & Mandt, S. (2022) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv51458.2022.00100 · Cited by 113
“With the abundance of smartphones, autonomous drones, and other intelligent devices, advanced computing systems for machine learning applications have become evermore important [47, 10].”
BackgroundBhat, S. A., Sofi, I. B., & Chi, C. (2020) · IEEE Access · doi:10.1109/access.2020.3037108 · Cited by 97
“Recent works in the literature address AI in a diverse perception of edge computing, IoT, and networks [124], [141]–[153].”
BackgroundKey Advances in Pervasive Edge Computing for Industrial Internet of Things in 5G and Beyond
Narayanan, A., Sena, A. S. D., Gutierrez-Rojas, D., Melgarejo, D. C., Hussain, H. M., Ullah, M., Bayhan, S., & Nardelli, P. H. J. (2020) · IEEE Access · doi:10.1109/access.2020.3037717 · Cited by 77
“In a recent paper, Chen et al. surveyed research literature at the confluence of DL and PEC [67].”
BackgroundApplications and Techniques for Fast Machine Learning in Science
Deiana, A. M., Tran, N. V., Agar, J., Blott, M., Guglielmo, G. D., Duarte, J. M., Harris, P. C., Hauck, S., Liu, M., Neubauer, M. S., et al. (2022) · Frontiers in Big Data · doi:10.3389/fdata.2022.787421 · Cited by 126
ARES: Adaptive Resource-Aware Split Learning for Internet of Things
Samikwa, E., Maio, A. D., & Braun, T. I. (2022) · Computer Networks · doi:10.1016/j.comnet.2022.109380 · Cited by 101
Moving Deep Learning to the Edge
Véstias, M. P., Duarte, R. P., de Sousa, J. T., & Neto, H. C. (2020) · Algorithms · doi:10.3390/a13050125 · Cited by 73
“Previous reviews on the same subject have focused on the deployment of DL methods, such as Deep Neural Networks (DNN), into edge computing, with an emphasis on how the edge infrastructure is used for inference and training [13,18,24].”
BackgroundReconfigurable Intelligent Surface for Green Edge Inference
Hua, S., Zhou, Y., Yang, K., Shi, Y., & Wang, K. (2021) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2021.3058657 · Cited by 74
“While the model compression [7], model selection [8], and hardware acceleration [9] are proposed as promising techniques to help devices run small-sized DNN models, deploying powerful models with millions of parameters is still challenging because of both the memory and battery limitations [10].”
MethodInternet of things: Conceptual network structure, main challenges and future directions
Furstenau, L. B., Rodrigues, Y. P. R., Sott, M. K., Leivas, P. D. O., Dohan, M. S., López-Robles, J. R., Cobo, M. J., Bragazzi, N. L., & Choo, K. R. (2022) · Digital Communications and Networks · doi:10.1016/j.dcan.2022.04.027 · Cited by 92
Rijwani, T., Kumari, S., Srinivas, R., Abhishek, K., Iyer, G., Vara, H., Dubey, S., Revathi, V., & Gupta, M. (2024) · International Journal on Interactive Design and Manufacturing (IJIDeM) · doi:10.1007/s12008-024-01943-7 · Cited by 117
“Chen et al. [15] have discussed the increasing use of deep learning in various applications, such as computer vision and natural language processing, where end devices like smartphones and IoT sensors generate data requiring real-time analysis or model training.”
Reconfigurable Intelligent Surface Assisted Mobile Edge Computing With Heterogeneous Learning Tasks
Huang, S., Wang, S., Wang, R., Wen, M., & Huang, K. (2021) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2021.3056707 · Cited by 75
“, model sharing and data sharing [2], [6], [7].”
Machine Learning for Emergency Management: A Survey and Future Outlook
Kyrkou, C., Kolios, P., Theocharides, T., & Polycarpou, M. M. (2022) · Proceedings of the IEEE · doi:10.1109/jproc.2022.3223186 · Cited by 100
“The availability of multiple and diverse data is key in enabling the employment of ML in emergency management solutions [40].”
BackgroundApplications of Machine Learning in Networking: A Survey of Current Issues and Future Challenges
Ridwan, M. A., Radzi, N. A. M., Abdullah, F., & Jalil, Y. E. (2021) · IEEE Access · doi:10.1109/access.2021.3069210 · Cited by 88
Enabling Resource-Efficient AIoT System With Cross-Level Optimization: A Survey
Liu, S., Guo, B., Fang, C., Wang, Z., Luo, S., Zhou, Z., & Yu, Z. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3319952 · Cited by 83
“The most related previous surveys include [13], [14], [15], [16], [17].”
BackgroundComputation offloading in Edge Computing environments using Artificial Intelligence techniques
Carvalho, G., Cabral, B., Pereira, V., & Bernardino, J. (2020) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2020.103840 · Cited by 74
Cloud Versus Edge Deployment Strategies of Real-Time Face Recognition Inference
Koubaa, A., Ammar, A., Kanhouch, A., & AlHabashi, Y. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2021.3055835 · Cited by 69
“…and did not investigate the effect of model optimization using TFLite and TensorRT, as we proposed in this paper Wang et al. [14], and Chen and Ran [25] presented theoretical surveys that compared several edge computation and communication modes used in the literature (integral or partial…”
MethodA review of zirconia oxygen, NOx, and mixed potential gas sensors – History and current trends
Halley, S., Ramaiyan, K. P., Tsui, L., & Garzón, F. H. (2022) · Sensors and Actuators B Chemical · doi:10.1016/j.snb.2022.132363 · Cited by 74
Joint Privacy Enhancement and Quantization in Federated Learning
Lang, N., Sofer, E., Shaked, T., & Shlezinger, N. (2023) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2023.3244092 · Cited by 97
“Federated learning (FL) [2], [3], [4], [5] is an emerging paradigm for training on edge devices, exploiting their computational capabilities [6].”
Large Language Models Meet Next-Generation Networking Technologies: A Review
Hang, C.-N., Yu, P.-D., Morabito, R., & Tan, C.-W. (2024) · Future Internet · doi:10.3390/fi16100365 · Cited by 64
Du, Y., Mukherjee, T., Li, R., Hou, Z., Dutta, S., Arnold, C. B., Elwany, A. H., Kung, S., Tang, J., & DebRoy, T. (2025) · Progress in Materials Science · doi:10.1016/j.pmatsci.2025.101587 · Cited by 99
DoSRA: A Decentralized Approach to Online Edge Task Scheduling and Resource Allocation
Peng, Q., Wu, C., Xia, Y., Ma, Y., Wang, X., & Jiang, N. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3107431 · Cited by 74
Prabhu, K., Gural, A., Khan, Z. F., Radway, R. M., Giordano, M., Koul, K., Doshi, R., Kustin, J. W., Liu, T., Lopes, G. B., et al. (2022) · IEEE Journal of Solid-State Circuits · doi:10.1109/jssc.2022.3140753 · Cited by 79
Model-driven Cluster Resource Management for AI Workloads in Edge Clouds
Liang, Q., Hanafy, W. A., Ali-Eldin, A., & Shenoy, P. J. (2023) · ACM Transactions on Autonomous and Adaptive Systems · doi:10.1145/3582080 · Cited by 71
“Hardware accelerators such as GPUs and TPUs provide a powerful add-on for edge infrastructure [7, 34, 56].”
BackgroundDNN Surgery: Accelerating DNN Inference on the Edge Through Layer Partitioning
Liang, H., Sang, Q., Hu, C., Cheng, D., Zhou, X., Wang, D., Bao, W., & Wang, Y. (2023) · IEEE Transactions on Cloud Computing · doi:10.1109/tcc.2023.3258982 · Cited by 87
“data source, edge computing emerges [7].”
Lan, Y., Huang, K., Yang, C. I., Lei, L., Ye, J., Zhang, J., Zeng, W., Zhang, Y., & Deng, J. (2021) · Remote Sensing · doi:10.3390/rs13214370 · Cited by 76
Communication-efficient distributed AI strategies for the IoT edge
Mwase, C., Jin, Y., Westerlund, T., Tenhunen, H., & Zou, Z. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.01.013 · Cited by 74
CNNPC: End-Edge-Cloud Collaborative CNN Inference With Joint Model Partition and Compression
Yang, S., Zhang, Z., Zhao, C., Song, X., Guo, S., & Li, H. (2022) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2022.3177782 · Cited by 73
“…cloud-based AI requires such enormous data to be transmitted from the network edge to the Cloud, where various fundamental concerns on response latency, cloud bandwidth, and data privacy preservation are revealed and severely hindering the landing of urgently required AI applications [10], [12].”
BackgroundGültekın, Ö., Çinar, E. M., Özkan, K., & Yazıcı, A. T. (2022) · Sensors · doi:10.3390/s22093208 · Cited by 82
“Thus, utilizing edge AI techniques decreases communication costs and latency and increases reliability, scalability, data security, and privacy [30].”
BackgroundIIoT Malware Detection Using Edge Computing and Deep Learning for Cybersecurity in Smart Factories
Kim, H.-M., & Lee, K. (2022) · Applied Sciences · doi:10.3390/app12157679 · Cited by 82
EdgeDRNN: Recurrent Neural Network Accelerator for Edge Inference
Gao, C., Ríos-Navarro, A., Chen, X., Liu, S., & Delbrück, T. (2020) · IEEE Journal on Emerging and Selected Topics in Circuits and Systems · doi:10.1109/jetcas.2020.3040300 · Cited by 70
Real-Time Semantic Segmentation via Spatial-Detail Guided Context Propagation
Hao, S., Zhou, Y., Guo, Y., Hong, R., Cheng, J. S., & Wang, M. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3154443 · Cited by 75
“Recently, the success of deep learning has simultaneously brought opportunities and challenges to edge computing [9], [10].”
Video Fire Detection Methods Based on Deep Learning: Datasets, Methods, and Future Directions
Jin, C., Wang, T., Alhusaini, N., Zhao, S., Liu, H., Xu, K., & Zhang, J. (2023) · Fire · doi:10.3390/fire6080315 · Cited by 85
Javaid, S., Khalil, R. A., Saeed, N., He, B., & Alouini, M. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3522103 · Cited by 92
“Future work should also explore the distributed processing mechanisms for LLM predictions and adjustments locally to reduce the need for data to travel to centralized servers to minimize latency and improve the efficiency of power management strategies [222]–[224], [246].”
Optimising Deep Learning at the Edge for Accurate Hourly Air Quality Prediction
Wardana, I. N. K., Gardner, J. W., & Fahmy, S. A. (2021) · Sensors · doi:10.3390/s21041064 · Cited by 61
“Both ASICs and FPGAs are generally more energy-efficient than conventional CPUs and GPUs [4].”
BackgroundMethodInfluentialTurner, C. J., Ma, R., Chen, J., & Oyekan, J. O. (2021) · IEEE Access · doi:10.1109/access.2021.3099311 · Cited by 86
“Chen et al. [97] and Sun et al. [98] acknowledge the value of Edge in the delivery of manufacturing and industrial solutions to the need for localized processing of data streams, with the assistance of machine learning techniques [99] including Deep Learning [100], [33].”
BackgroundMethodSelf-citationDVFO: Learning-Based DVFS for Energy-Efficient Edge-Cloud Collaborative Inference
Zhang, Z., Zhao, Y., Li, H., Lin, C., & Liu, J. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3357218 · Cited by 99
“…of Things (IoT) connectivity and hardware accelerators (e.g., GPUs) are becoming capable of executing deep neural network (DNN) in real-time for many edge intelligence [2] applications, such as defect detection [3], face recognition [4], and mobile augmented reality [5], just to name a few.”
BackgroundCurrent approaches and future directions for Cyber Threat Intelligence sharing: A survey
Alaeifar, P., Pal, S., Jadidi, Z., Hussain, M., & Foo, E. (2024) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2024.103786 · Cited by 128
Fast and Accurate Streaming CNN Inference via Communication Compression on the Edge
Hu, D., & Krishnamachari, B. (2020) · IEEE/ACM International Conference on Internet-of-Things Design and Implementation (IoTDI) · doi:10.1109/iotdi49375.2020.00023 · Cited by 72
“Many applications such as smart city, smart grid and Virtual Reality expect data to be analyzed locally on the resource-constrained edge devices [10].”
BackgroundFrom Molecular Electronics to Molecular Intelligence
Yan, C., Fang, C., Gan, J., Wang, J., Zhao, X. Z., Wang, X., Li, J., Zhang, Y., Liu, H., Li, X., et al. (2024) · ACS Nano · doi:10.1021/acsnano.4c10389 · Cited by 62
Matsubara, Y., Callegaro, D., Singh, S., Levorato, M., & Restuccia, F. (2022) · IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM) · doi:10.1109/wowmom54355.2022.00032 · Cited by 90
Knowledge Distillation Facilitates the Lightweight and Efficient Plant Diseases Detection Model
Huang, Q., Wu, X., Wang, Q., Dong, X., Qin, Y., Wu, X. M., Gao, Y., & Hao, G. (2023) · Plant Phenomics · doi:10.34133/plantphenomics.0062 · Cited by 69
Edge MLOps: An Automation Framework for AIoT Applications
Raj, E., Buffoni, D., Westerlund, M., & Ahola, K. (2021) · 2021 IEEE International Conference on Cloud Engineering (IC2E) · doi:10.1109/ic2e52221.2021.00034 · Cited by 52
“Further studies have described how to perform inference of AI and more specifically Machine Learning (ML) on the edge [13], [14], [15].”
BackgroundRai, N., & Sun, X. (2024) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2024.108792 · Cited by 66
Neto, E. C. P., Iqbal, S., Buffett, S., Sultana, M., & Taylor, A. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11346-z · Cited by 105
Resource-Constrained Neural Architecture Search on Edge Devices
Lyu, B., Yuan, H., Lu, L., & Zhang, Y. (2021) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2021.3054583 · Cited by 64
Mamat, N., Othman, M. F., Abdoulghafor, R., Belhouari, S. B., Mamat, N., & Hussein, S. F. M. (2022) · Agriculture · doi:10.3390/agriculture12071033 · Cited by 68
“This is because the training process is both space consuming and computationally intensive, as millions of parameters are needed to refine over multiple periods of time [34].”
BackgroundHuman Activity Recognition on Microcontrollers with Quantized and Adaptive Deep Neural Networks
Daghero, F., Burrello, A., Xie, C., Castellano, M., Gandolfi, L., Calimera, A., Macii, E., Poncino, M., & Pagliari, D. J. (2022) · ACM Transactions on Embedded Computing Systems · doi:10.1145/3542819 · Cited by 67
“On-device inference avoids the transmission of large amounts of (possibly privacysensitive) data to the cloud over energy hungry wireless channels, which may become slow or unavailable in bad connectivity areas [10, 12].”
BackgroundEnabling All In-Edge Deep Learning: A Literature Review
Joshi, P., Hasanuzzaman, M., Thapa, C., Afli, H., & Scully, T. (2023) · IEEE Access · doi:10.1109/access.2023.3234761 · Cited by 77
“Unlike prior surveys [13], [15], [16], [17], [18],”
Swaminathan, T. P., Silver, C., Akilan, T., & Kumar, J. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.03.273 · Cited by 78
Wireless Edge Machine Learning: Resource Allocation and Trade-Offs
Merluzzi, M., Lorenzo, P. D., & Barbarossa, S. (2021) · IEEE Access · doi:10.1109/access.2021.3066559 · Cited by 66
Edge deep learning for neural implants: a case study of seizure detection and prediction
Liu, X., & Richardson, A. G. (2021) · Journal of Neural Engineering · doi:10.1088/1741-2552/abf473 · Cited by 71
Manufacturing as a Data-Driven Practice: Methodologies, Technologies, and Tools
Cerquitelli, T., Pagliari, D. J., Calimera, A., Bottaccioli, L., Patti, E., Acquaviva, A., & Poncino, M. (2021) · Proceedings of the IEEE · doi:10.1109/jproc.2021.3056006 · Cited by 78
“More-over, the transmission of large data sizes from in-field edge devices to the cloud also has a high energy cost, which can be significantly reduced by doing prediction at the edge [74].”
BackgroundMethodLow Latency Deep Learning Inference Model for Distributed Intelligent IoT Edge Clusters
Naveen, S., Kounte, M. R., & Ahmed, M. R. (2021) · IEEE Access · doi:10.1109/access.2021.3131396 · Cited by 77
Adibnia, E., Mansouri-Birjandi, M. A., Ghadrdan, M., & Jafari, P. (2024) · Scientific Reports · doi:10.1038/s41598-024-56522-3 · Cited by 63
Lyapunov-Based Optimization of Edge Resources for Energy-Efficient Adaptive Federated Learning
Battiloro, C., Lorenzo, P. D., Merluzzi, M., & Barbarossa, S. (2022) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2022.3186879 · Cited by 62
Tuli, S., Casale, G., & Jennings, N. R. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3177569 · Cited by 67
“Example of common worker nodes in edge environments include Raspberry Pis, Arduino and similar System-on-Chip (SoC) computers [2].”
BackgroundCollaborative Inference for AI-Empowered IoT Devices
Shlezinger, N., & Bajić, I. V. (2022) · IEEE Internet of Things Magazine · doi:10.1109/iotm.001.2200152 · Cited by 60
“However, edge devices do not share these computational and storage resources, and tend to be notably more limited in compute and power compared with powerful centralized servers [1].”
BackgroundOnline Meta-Learning for Hybrid Model-Based Deep Receivers
Raviv, T., Park, S., Simeone, O., Eldar, Y. C., & Shlezinger, N. (2023) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2023.3241841 · Cited by 75
“Furthermore, the rapid growth and expected proliferation of dedicated hardware accelerators We note that in Algorithm 1 the number of iterations is given by constants I sgd and I meta for online and meta-learning, respectively.”
BackgroundReal-Time Detection of DDoS Attacks Based on Random Forest in SDN
Ma, R., Wang, Q., Bu, X., & Chen, X. (2023) · Applied Sciences · doi:10.3390/app13137872 · Cited by 72
Quantum-Inspired Optimization Algorithms for Scalable Machine Learning in Edge Computing
Goyal, R., Kumar, K., Sharma, V., Bhutia, R., Jain, A., & Kumar, M. (2024) · International Conference on Technological Advancements in Computational Sciences (ICTACS) · doi:10.1109/ictacs62700.2024.10840586 · Cited by 56
“Although still in its infancy, quantum computing has proven rather effective in solving highly nontrivial optimization problems that are beyond the capabilities of a classical PC [7].”
Wireless Avionics Intracommunications: A Survey of Benefits, Challenges, and Solutions
Park, P., Marco, P. D., Nah, J., & Fischione, C. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.3038848 · Cited by 59
“The recent integration of DL and edge computing essentially solves the problem of the high-computation and low-latency requirements of the data-driven fault-detection and diagnosis [44].”
BackgroundEnergy-Efficient Service Placement for Latency-Sensitive Applications in Edge Computing
Premsankar, G., & Ghaddar, B. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3162581 · Cited by 65
“E DGE computing allows applications to be hosted closer to end users by bringing computing, storage, and networking resources to the edge of the network [1]–[3].”
BackgroundA Comprehensive Survey on Collaborative Data-access Enablers in the IIoT
Sun, D., Hu, J., Wu, H., Wu, J. X., Yang, J. Y., Sheng, Q. Z., & Dustdar, S. (2023) · ACM Computing Surveys · doi:10.1145/3612918 · Cited by 63
“For this reason, they are a popular choice for applications with large-scale mobile data [37, 193].”
BackgroundSu, Y., Fan, W., Gao, L. H., Qiao, L., Liu, Y., & Wu, F. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3219058 · Cited by 60
“DL inference acceleration can be divided into two aspects: 1) task offloading; 2) DNN partition and deployment [1].”
BackgroundMethodLightweight Compression Of Neural Network Feature Tensors For Collaborative Intelligence
Cohen, R. A., Choi, H., & Bajic, I. V. (2020) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme46284.2020.9102797 · Cited by 68
“With recent advances in machine learning and their efficient implementations, we are beginning to see an increasingly widespread use of deep neural networks (DNNs) on small or lightweight platforms such as mobile devices, edge computing systems, and embedded platforms [1–3].”
A Systematic Assessment of Embedded Neural Networks for Object Detection
Verucchi, M., Brilli, G., Sapienza, D., Verasani, M., Arena, M., Gatti, F., Capotondi, A., Cavicchioli, R., Bertogna, M., & Solieri, M. (2020) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa46521.2020.9212130 · Cited by 67
“Regarding fast inference on-device computation, three major axes efforts have been identified [7] to maximise performances or contain power consumption. a) Network model design: Reducing the number of parameters in the DNN model is very common approach to reduce memory and execution latency, while…”
Hussain, D., Al‐masni, M. A., Aslam, M., Sadeghi‐Niaraki, A., Hussain, J., Gu, Y. H., & Naqvi, R. A. (2024) · Journal of X-Ray Science and Technology · doi:10.3233/xst-230429 · Cited by 82
Jamil, M. N., Schelén, O., Monrat, A. A., & Andersson, K. (2024) · IEEE Access · doi:10.1109/access.2024.3454812 · Cited by 80
Federated deep reinforcement learning based secure data sharing for Internet of Things
Miao, Q., Lin, H., Wang, X., & Hassan, M. M. (2021) · Computer Networks · doi:10.1016/j.comnet.2021.108327 · Cited by 53
“Using deep learning in edge networks can ensure privacy and security and improve bandwidth efficiency [20].”
Key Considerations for Real-Time Object Recognition on Edge Computing Devices
Surantha, N., & Sutisna, N. (2025) · Applied Sciences · doi:10.3390/app15137533 · Cited by 63
Traffic big data assisted V2X communications toward smart transportation
An, C., & Wu, C. (2019) · Wireless Networks · doi:10.1007/s11276-019-02181-6 · Cited by 47
“Chen and Ran reviewed the current research efforts on the deep learning for edge computing [30].”
BackgroundPérez, S., Arroba, P., & Moya, J. M. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2021.07.031 · Cited by 51
Optimization of Edge-PLC-Based Fault Diagnosis With Random Forest in Industrial Internet of Things
Liu, P., Zhang, Y., Wu, H., & Fu, T. (2020) · IEEE Internet of Things Journal · doi:10.1109/jiot.2020.2994200 · Cited by 52
“However, there are some potential problems with using such a data migration approach, such as latency, scalability, and privacy [12].”
BackgroundPipeEdge: Pipeline Parallelism for Large-Scale Model Inference on Heterogeneous Edge Devices
Hu, Y., Imes, C., Zhao, X., Kundu, S., Beerel, P. A., Crago, S. P., & Walters, J. P. (2022) · Euromicro Conference on Digital System Design (DSD) · doi:10.1109/dsd57027.2022.00048 · Cited by 75
Ahmed, M., Raza, S., Soofi, A. A., Khan, F., Khan, W. U., Xu, F., Chatzinotas, S., Dobre, O. A., Han, Z., & Han, Z. (2024) · Computer Science Review · doi:10.1016/j.cosrev.2024.100668 · Cited by 56
3D stacked IGZO 2T0C DRAM array with multibit capability for computing in memory applications
Li, Q., Hu, Q., Zhu, S., Zeng, M., Zhao, W., & Wu, Y. (2025) · Science Advances · doi:10.1126/sciadv.adu4323 · Cited by 58
“With massive edge devices deployed in the physical world, processing high-resolution images is a highly demanding quest for artificial intelligence (AI) to understand the environment ( 1 ).”
Exploring edge TPU for network intrusion detection in IoT
Hosseininoorbin, S., Layeghy, S., Sarhan, M., Jurdak, R., & Portmann, M. (2023) · Journal of Parallel and Distributed Computing · doi:10.1016/j.jpdc.2023.05.001 · Cited by 60
The Many Faces of Edge Intelligence
Peltonen, E., Ahmad, I., Aral, A., Capobianco, M., Ding, A. Y., Gil‐Castiñeira, F., Gilman, E., Harjula, E., Jurmu, M., Karvonen, T., et al. (2022) · IEEE Access · doi:10.1109/access.2022.3210584 · Cited by 55
“in prior surveys [2] [16]: Smart Cities, Industrial IoT, and Environmental Monitoring.”
BackgroundExploring Edge TPU for Network Intrusion Detection in IoT
Hosseininoorbin, S., Layeghy, S., Sarhan, M., Jurdak, R., & Portmann, M. (2021) · arXiv · doi:10.48550/arxiv.2103.16295 · Cited by 45
The Communication-Aware Clustered Federated Learning Problem
Shlezinger, N., Rini, S., & Eldar, Y. C. (2020) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit44484.2020.9174245 · Cited by 53
“Larger values of m c allows for learning of more accurate individual models, and thus yield better inference on the edge devices [5].”
BackgroundRishi Vardhan, K., Vedanth, S., Poojah, G., Abhishek, K., Kumar, M. N., & Vijayaraghavan, V. (2021) · International Conference on Machine Learning and Applications · doi:10.1109/icmla52953.2021.00241 · Cited by 60
Taha, Z. K., Yaw, C. T., Koh, S. P., Kiong, T. S., Kadirgama, K., Benedict, F., Tan, J. D., & Balasubramaniam, Y. (2023) · IEEE Access · doi:10.1109/access.2023.3267964 · Cited by 59
“These challenges can be overcome by using mobile edge computing to harness the processing power of edge devices and enable training at the network edge without the need for data sharing [3].”
BackgroundZhu, K., & Yan, B. (2023) · Materials Horizons · doi:10.1039/d3mh01253k · Cited by 43
Energy-efficient deep learning inference on edge devices
Daghero, F., Pagliari, D. J., & Poncino, M. (2020) · Advances in computers · doi:10.1016/bs.adcom.2020.07.002 · Cited by 49
Single-layer vision transformers for more accurate early exits with less overhead
Bakhtiarnia, A., Zhang, Q., & Iosifidis, A. (2022) · Neural Networks · doi:10.1016/j.neunet.2022.06.038 · Cited by 58
Shome, D., Waqar, O., & Khan, W. U. (2022) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.4458 · Cited by 51
“, Graphical Processing Units (GPU) [15].”
Southworth, J., Smith, A. C., Safaei, M., Rahaman, M., Alruzuq, A., Tefera, B. B., Muir, C. S., & Herrero, H. V. (2024) · Frontiers in Remote Sensing · doi:10.3389/frsen.2024.1374862 · Cited by 53
Feng, J., Yu, T., Zhang, K., & Cheng, L. (2025) · Processes · doi:10.3390/pr13041144 · Cited by 77
Model-Based Deep Learning: Key Approaches and Design Guidelines
Shlezinger, N., Whang, J., Eldar, Y. C., & Dimakis, A. G. (2021) · IEEE Data Science Workshop (DSW) · doi:10.1109/dslw51110.2021.9523403 · Cited by 54
“This severely limits their applicability on hardware-limited and portable devices [2].”
BackgroundOptimizing Edge AI: A Comprehensive Survey on Data, Model, and System StrategiesPreprint
Wang, X., & Jia, W. (2025) · Qeios · doi:10.32388/izohch · Cited by 56
Singh, D., Akram, S. V., Singh, R., Gehlot, A., Buddhi, D., Priyadarshi, N., Sharma, G., & Bokoro, P. N. (2022) · Electronics · doi:10.3390/electronics11172700 · Cited by 46
Edge-Assisted On-Device Model Update for Video Analytics in Adverse Environments
Kong, Y., Yang, P., & Cheng, Y. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3612585 · Cited by 53
“is because edge computing can help to meet the rigorous demands of video analytics tasks due to its availability in the proximity of source video cameras [4, 9, 34, 40, 45, 52].”
Background
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.