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 901–1,000 of 1,000
Blind Video Quality Assessment at the Edge
Mei, Z., Wang, Y.-C., & Kuo, C. ‐. J. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3521704 · Cited by 5
“The remarkable success achieved by DL in various domains, such as computer vision and natural language processing, has inspired the application of DL to edge devices (say, smartphones and IoT sensors) [43].”
NLU: An Adaptive, Small-Footprint, Low-Power Neural Learning Unit for Edge and IoT Applications
Rostami, A., Zeinolabedin, S. M. A., Guo, L., Kelber, F., Bauer, H., Dixius, A., Scholze, S., Berthel, M., Walter, D., Uhlig, J., et al. (2025) · IEEE Open Journal of Circuits and Systems · doi:10.1109/ojcas.2025.3546067 · Cited by 8
“Additionally, in wearable devices, eliminating communication with cloud servers can reduce power consumption and extend battery life [13], [14], [15], [16], [17], [18].”
Interpretable deep model pruning
Huang, H., & Pao, H.-K. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130485 · Cited by 4
Redefining frontiers of computational imaging with deep learning
Zhong, T., Huang, H., Li, H., Park, Y., & Lai, P. (2025) · Photonics Insights · doi:10.3788/pi.2025.c04 · Cited by 3
Long Short-Term Memory with Spin-Based Binary and Non-Binary Neurons
Sheikhfaal, S., Vangala, M. R., Adepegba, A., & DeMara, R. F. (2021) · IEEE International Midwest Symposium on Circuits and Systems (MWSCAS) · doi:10.1109/mwscas47672.2021.9531773 · Cited by 3
Flamis, G., Kalapothas, S., & Kitsos, P. (2021) · South-East Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conference (SEEDA-CECNSM) · doi:10.1109/seeda-cecnsm53056.2021.9566259 · Cited by 3
Big–Little Adaptive Neural Networks on Low-Power Near-Subthreshold Processors
Shen, Z., Howard, N., & Nunez-Yanez, J. L. (2022) · Journal of Low Power Electronics and Applications · doi:10.3390/jlpea12020028 · Cited by 4
“Due to high latency and privacy issues, cloud computing tasks are gradually being transferred to the edge in areas such as image recognition and natural language processing [2].”
BackgroundSpike-Event X-ray Image Classification for 3D-NoC-Based Neuromorphic Pneumonia Detection
Wang, J., Ikechukwu, O. M., Dang, K. N., & Abdallah, A. B. (2022) · Electronics · doi:10.3390/electronics11244157 · Cited by 3
Actor Critic Approach based Anomaly Detection for Edge Computing Environments
Shruthi, N. K., & Siddesh, G. K. (2023) · International journal of Computer Networks & Communications · doi:10.5121/ijcnc.2023.15104 · Cited by 5
PalmMatchDB: An On-Device Contactless Palmprint Recognition Corpus
Alausa, D. W. S., Adetiba, E., Badejo, J. A., Davidson, I. E. A., Akindeji, K. T., Obiyemi, O. O., & Abayomi, A. (2023) · IEEE International Conference on Power, Electronics and Computer Applications (ICPECA) · doi:10.1109/icpeca56706.2023.10076097 · Cited by 3
“It features a variety of standard hardware interfaces that make it easy to integrate with a wide range of products and form factors [16].”
BackgroundLow-Cost Image Search System on Off-Line Situation
Diana, M., Chikama, J., Amagasaki, M., & Iida, M. (2020) · Electronics · doi:10.3390/electronics9010153 · Cited by 3
“The highest value of cosine similarity indicates that two vectors are almost similar.”
BackgroundAccelerating on-device DNN inference during service outage through scheduling early exit
Wang, Z., Bao, W., Yuan, D., Ge, L., Tran, N. H. K., & Zomaya, A. Y. (2020) · Computer Communications · doi:10.1016/j.comcom.2020.08.005 · Cited by 6
Combining multiple data sources and enriching the dataset using Industrial Edge Devices
Dumss, S., Grafinger, M., Hennig, M. J. P., & Rosenberger, P. (2020) · Procedia CIRP · doi:10.1016/j.procir.2020.03.081 · Cited by 3
Teti, M., Hahn, W. E., Martin, S., Teti, C., & Barenholtz, E. (2021) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2021.103780 · Cited by 3
Application of IOT deep learning in edge computing: a review
Li, H. (2021) · Academic Journal of Computing & Information Science · doi:10.25236/ajcis.2021.040514 · Cited by 6
“The process also has a high delay [10].”
BackgroundA library-based tool to translate high level DNN models into hierarchical VHDL descriptions
Rubio‐Ibáñez, P., Martínez-Álvarez, J. J., & Doménech‐Asensi, G. (2021) · Conference on Design of Circuits and Integrated Systems · doi:10.1109/dcis53048.2021.9666161 · Cited by 3
Edge Computing as an Architectural Solution: An Umbrella Review
Bandi, A., & Alegría, J. A. H. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-0019-8_45 · Cited by 3
Leotta, F., Mathew, J. G., Mecella, M., & Monti, F. (2022) · Lecture notes in business information processing · doi:10.1007/978-3-031-07478-3_10 · Cited by 3
Energy-Efficient Collaborative Inference in MEC: A Multi-Agent Reinforcement Learning Based Approach
Xiao, Y., Wan, K., Liang, X., & Yang, H. (2022) · International Conference on Big Data Computing and Communications (BigCom) · doi:10.1109/bigcom57025.2022.00057 · Cited by 3
“Collaborative inference leverages the computational resources of both the mobile device and the edge server to support the deep learning based perception services, such as object detection [1]–[4].”
BackgroundPRISM: Privacy Preserving Healthcare Internet of Things Security Management
Hadjixenophontos, S., Mandalari, A. M., Zhao, Y., & Haddadi, H. (2023) · IEEE Symposium on Computers and Communications (ISCC) · doi:10.1109/iscc58397.2023.10218268 · Cited by 5
“now are capable of conducting advanced tasks such as training DNN models and using them for local inference [21], [22].”
MethodState-of-the-art Techniques in Deep Edge IntelligencePreprint
Lodhi, A. H., Akgün, B., & Özkasap, Ö. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2008.00824 · Cited by 5
“[8] Modes of DEI deployment across Edge nodes for training and inference • Identify various scenarios for optimal execution of DEI schemes on end-devices • Model Splitting between devices and edge nodes and cloud servers • Resource management • DEI benchmarking • Convergence of DEI with network abstraction schemes”
Digital Twin Coaching for Edge Computing Using Deep Learning Based 2D Pose Estimation
Díaz, R. G. (2021) · uO Research (University of Ottawa) · doi:10.20381/ruor-26229 · Cited by 5
“Most of the devices mentioned are designed to be portable and as independent as possible, so the priority is to consume as few resources as possible [55].”
BackgroundMateos, C., Hirsch, M., Toloza, J. M., & Zunino, A. (2022) · SoftwareX · doi:10.1016/j.softx.2022.101268 · Cited by 3
Variable Precision Multiplier for CNN Accelerators Based on Booth Algorithm
Guem, D.-H., & Kim, S. (2023) · International Journal on Advanced Science Engineering and Information Technology · doi:10.18517/ijaseit.13.3.18456 · Cited by 3
Niu, X., Cao, X., Chen, Y., & Jin, H. (2024) · ACM Transactions on Sensor Networks · doi:10.1145/3652516 · Cited by 2
Tool remaining life prediction based on edge computing and AT-LSTM recurrent neural network
Wang, T., Luo, J. L., Jinbing, C., Ma, L., Wang, B., & Ren, S. (2024) · IEEE Conference on Prognostics and Health Management · doi:10.1109/icphm61352.2024.10626985 · Cited by 2
Machine learning approaches for tsunami early warning
Mulia, I. E. (2024) · Elsevier eBooks · doi:10.1016/b978-0-443-18987-6.00012-9 · Cited by 7
Applications of IoT and Edge Computing in Medical Informatics for Real-Time Patient Monitoring
Varma, P., Meher, K., Choudhury, S., Swathi, V., Kandhari, H., Taneja, M., & Awasthi, S. (2024) · Seminars in Medical Writing and Education · doi:10.56294/mw2024505 · Cited by 3
DistrEE: Distributed Early Exit of Deep Neural Network Inference on Edge Devices
Peng, X., Wu, X., Xu, L., Wang, L., & Fei, A. (2024) · Globecom · doi:10.1109/globecom52923.2024.10901763 · Cited by 5
“However, these methods can excessively compress the network, resulting in a decrease in inference accuracy, and they heavily rely on unreliable wide area network connections [3].”
Picot, R., de Magalhães, F. G., Bushehri, A. S., Atti, M. B., Nicolescu, G., & Quintero, A. (2025) · IEEE Access · doi:10.1109/access.2025.3555201 · Cited by 3
Kumar, P. V., & Marimuthu, C. N. (2025) · International Journal of Distributed Sensor Networks · doi:10.1155/dsn/5651009 · Cited by 2
“However, these algorithms require further optimization for implementation on resource-constrained edge-based WSN devices [12].”
Enhanced wildfire detection and semantic segmentation via fine-tuned deep learning models
Quang, N. H., Lee, H., Ahn, S., & Kim, G. (2025) · Earth Science Informatics · doi:10.1007/s12145-025-01863-4 · Cited by 4
“Besides, it is worth considering the model sizes in case of balance between accuracy and computing efficiency in terms of available resources, required speed, and type of operations of post-assessment, real-time e.g. (Chen and Ran 2019).”
Malhotra, A., & Gupta, S. K. (2025) · IEEE Transactions on Circuits and Systems I Regular Papers · doi:10.1109/tcsi.2025.3570193 · Cited by 3
“R ECENTLY, there has been an immense interest in design techniques that can enhance the energy efficiency of deep neural networks (DNNs) and enable their deployment on the edge [1].”
Pacini, T., Nannipieri, P., Moranti, S., & Fanucci, L. (2025) · IEEE Access · doi:10.1109/access.2025.3577908 · Cited by 4
Liu, X., Li, B., Chen, S., & Xu, Z. (2025) · Electronics · doi:10.3390/electronics14122401 · Cited by 5
Wan, Y., Tian, X., He, H., Peng, T., Gao, R., Ji, X., Li, S., Luo, S., Li, W., & Chen, Z. (2025) · Processes · doi:10.3390/pr13061917 · Cited by 4
FLARE: Federated Lightweight Agents for Reinforcement Environments in Microgrids
Sang, Z., Duan, Z., Shen, S., Zhang, C., Wang, X., Luo, T., Chen, S., Wang, X., & Wu, G. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3587010 · Cited by 2
“With the advancement of large-scale model technologies, particularly the emergence of large language models(LLM) [68], the parameter count of deep learning models has grown exponentially, leading to substantial demands on computational and storage resources [69].”
Advancements in Defense Mechanisms against Adversarial Attacks in Computer Vision
Banait, S. S., Anish, C., Sen, M., Mondal, D., Dhabliya, D., & Kumar, J. R. R. (2024) · International Conference on Information Management & Machine Intelligence (ICIMMI) · doi:10.1145/3745812.3745886 · Cited by 3
Lyu, Y., Liu, L., Wang, X., Fan, Z., Wang, J., & Gao, G. (2025) · Machine Learning and Knowledge Extraction · doi:10.3390/make7040117 · Cited by 4
“To reduce the computational workloads on local devices, one approach is to offload video content to a more powerful edge or cloud for more efficient analytics [3,4].”
Optimized Implementation of YOLOv3-Tiny for Real-Time Image and Video Recognition on FPGA
Calì, R., Falaschetti, L., & Biagetti, G. (2025) · Electronics · doi:10.3390/electronics14203993 · Cited by 7
Khan, R., Saleh, H. H., Mefgouda, B., Alhussein, O., & Muhaidat, S. (2025) · Scientific Reports · doi:10.1038/s41598-025-20305-1 · Cited by 2
“Edge computing has emerged as a key paradigm for deploying machine learning (ML)-based intelligent systems in resource-constrained environments 30–33 .”
JORAS: joint offloading and resource auto-scaling in edge computing environment
Ghahari-Bidgoli, M., Ghobaei‐Arani, M., & Sharif, A. (2025) · Cluster Computing · doi:10.1007/s10586-025-05756-5 · Cited by 4
Han, T., Yang, Y., Tan, W., Bao, S., & Kuang, K. (2025) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001425520378 · Cited by 2
An FPGA-based accelerator design methodology for smart UAVs in precision agriculture: A case study
Bellocchi, G., Madroñal, D., Capotondi, A., Palumbo, F., & Marongiu, A. (2025) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2025.103592 · Cited by 2
Park, H., Shin, N., Kum, S., Kim, S. K., Kim, Y. Y., Choi, S., Won, D., & Suh, H. K. (2025) · Journal of Biosystems Engineering · doi:10.1007/s42853-025-00282-z · Cited by 2
“These devices have a limited amount of memory and processing power, which makes computational efficiency a crucial issue for deep learning algorithms (J. Chen & Ran, 2019; Voghoei et al., 2018).”
Bonny, T., Hammal, A. A., Nassan, W. A., & Elhoseny, M. (2025) · Network Modeling Analysis in Health Informatics and Bioinformatics · doi:10.1007/s13721-025-00600-7 · Cited by 2
Imankulov, T., Kenzhebek, Y., Bekele, S. D., & Akhmed-Zaki, D. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.108823 · Cited by 2
Online Scheduling With Trajectory Prediction for Collaborative DNN Inference in Vehicular Networks
Han, Z., Zhou, R., Tan, H. H., & Lui, J. C. S. (2025) · IEEE Transactions on Networking · doi:10.1109/ton.2025.3629759 · Cited by 2
“…for collaborative vehicle-edge inference, where the workload of DNN inference is split into two parts: the vehicle processes the initial computation, then transmits the intermediate data to a nearby RSU, which finishes the remaining computation and sends the results back to the vehicle [4].”
Golabi, A., Erradi, A., Said, A. B., Al-Ali, A., & Qidwai, U. (2026) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2026.103691 · Cited by 3
SecIDS-CNN-WF: A Trust-Aware Edge-Efficient CNN for Real-Time Wi-Fi Intrusion Detection
Almalkawi, I. T., Alhowaide, A., Al-Omari, A., Shtaiwi, S., & Zapata, M. G. (2026) · IEEE Access · doi:10.1109/access.2026.3656522 · Cited by 3
CECN-DNN: A cloud-edge collaborative inference approach to intrusion detection
Zhou, J., Zhang, X., Li, W., Zhan, X., Wang, Y., Li, W., He, Y., Ma, X., Xiong, Z., & Liu, H. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112127 · Cited by 3
A Low-Power Architecture for Passive Acoustic Autonomous Maritime Surveillance
Vasconcelos, H. M., Sousa, P. J. S. C. P., Dias, S., Pinto, J. P., van Golde, I., Tavares, P. J., & Moreira, P. (2026) · Journal of Marine Science and Engineering · doi:10.3390/jmse14090815 · Cited by 3
Yang, F., Yu, B., Zhou, Y., Luo, X., Tu, Z., & Liu, C. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115186 · Cited by 6
Protecting Machine Learning Integrity in Distributed Big Data Networking
Wei, Y., Chen, Y., Xiao, M., Maharjan, S., & Zhang, Y. (2020) · IEEE Network · doi:10.1109/mnet.011.1900450 · Cited by 3
“Distributed machine learning (DML) [2] is a platform with great potential to accommodate the needs of distributed and autonomous data processing in big data networking [3, 4].”
BackgroundAdaptive sparse ternary gradient compression for distributed DNN training in edge computing
Mao, Y., Wu, J., Xu, X., & Wang, L. (2022) · CCF Transactions on High Performance Computing · doi:10.1007/s42514-022-00091-2 · Cited by 2
“To process a large amount of input data and effectively improve the training efficiency (Chen and Ran 2019), edge computing uses the way of sinking the server’s resources like computing * Yingchi Mao yingchimao@hhu.”
MethodMao, Y., Wu, J., He, X., Ping, P., Wang, J., & Wu, J. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2022.3182394 · Cited by 2
“Specifically, some nodes may incur delays in computation or communication, which are called stragglers [8] [9].”
BackgroundUnderstanding and Applying Deep Learning
Lippmann, R. P. (2023) · Neural Computation · doi:10.1162/neco_a_01518 · Cited by 6
“…as small as a smartwatch using thousands of settings for simple applications, such as detecting when a short phrase is spoken to wake up a device (Chen & Ran, 2019), or it could be computed on a smartphone using a few million settings to recognize objects in images from a built-in camera (Howard…”
BackgroundEdgeMesh : A hybrid distributed training mechanism for heterogeneous edge devices
Xu, F., Feng, J., Zhang, Z., Ning, L., & Jia, Y. (2022) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.4706 · Cited by 2
“Considering the reduction of core network load, the typical solution 20,21,22 is to use knowledge distillation, federated learning, 23 and other technologies to offload DNN computing tasks on edge devices to an edge cloud or cloud computing platform to solve the performance shortage of edge devices.”
MethodAn Extensive Study on Logic Emerging IoT Adiabatic Techniques for Low-Power Circuit
Vijayalakshmi, T., & Selvakumar, J. (2023) · Engineering cyber-physical systems and critical infrastructures · doi:10.1007/978-3-031-18497-0_17 · Cited by 2
Nai, W., Chen, J., Wu, D., Yang, W., Xiang, Y., & Sajjanhar, A. (2023) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2023.103483 · Cited by 3
Self-citationA Proposed Method for Using Edge Computing to Secure Existing IoT Devices
Li, J., & Hu, Y. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-0416-7_79 · Cited by 2
Mozib, M. (2023) · International Journal of Science and Research (IJSR) · doi:10.21275/sr23603125305 · Cited by 2
Machine Learning Assisted Intelligent Reflecting Surface MIMO Communication-Gateway for 6G—A Review
Srivastava, P., & Khera, S. (2023) · Lecture notes in networks and systems · doi:10.1007/978-981-99-1479-1_40 · Cited by 3
Federated malware detection based on many‐objective optimization in cross‐architectural IoT
Zhang, Z., Zhang, Z., & Cui, Z. (2023) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.7919 · Cited by 2
Approximate arithmetic aware training for stochastic computing neural networks
Frasser, C. F., Morán, A., Canals, V., Font-Rosselló, J., Isern, E., Roca, M., & Rosselló, J. L. (2023) · Conference on Design of Circuits and Integrated Systems · doi:10.1109/dcis58620.2023.10336002 · Cited by 3
“T HE increasing popularity of intelligent edge devices employing Deep Learning (DL) models for inference tasks can be attributed to their advantages in terms of privacy, latency, bandwidth, energy, and cost over the traditional approach of sending sensor data to the cloud for analysis [1].”
BackgroundChannel-Adaptive Dynamic Neural Networks for Low-Complexity Distributed Signal Awareness
Abdi, M., Ashdown, J., Turck, K., & Restuccia, F. (2023) · IEEE Military Communications Conference (MILCOM) · doi:10.1109/milcom58377.2023.10356251 · Cited by 4
“At the other end of the spectrum, mobile devices may completely offload the computation to edge computers [24], also called edge computing , so as to achieve better task results while relieving the computation burden on mobile devices.”
BackgroundA Privacy-preserving Surface Defect Detection Scheme for Strip Steel
Tang, X., Zheng, X., Wang, X., & Huang, J. (2023) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac59482.2023.10401724 · Cited by 2
“Common compression methods include parameter quantization, parameter pruning and knowledge extraction [35], all of which help reduce the model overhead and make it work on resource-limited edge devices.”
Chen, Z., Bo, J., Wang, X., Jin, L., Qiao, X., Wang, B., Ding, Y., Qi, S., Zhai, Z., Wang, L., et al. (2024) · Offshore Technology Conference Asia · doi:10.4043/35024-ms · Cited by 2
Upadhyay, D., Malhotra, S., Gupta, M., & Mishra, S. (2024) · International Conference on Device Intelligence, Computing and Communication Technologies (DICCT) · doi:10.1109/dicct61038.2024.10532844 · Cited by 2
“Here, we delve into the innovative techniques of pruning and quantization, exploring their combined potential in refining the architecture of semantic segmentation networks [2].”
MethodBenchmarking Test-Time DNN Adaptation at Edge with Compute-In-Memory
Fan, Z., Wan, Z.-S., Liu, C.-K., Lu, A., Bhardwaj, K., & Raychowdhury, A. (2024) · ACM Journal on Autonomous Transportation Systems · doi:10.1145/3665898 · Cited by 6
“…the CIM paradigm is able to perform matrix-vector multiplication, the operation that is ubiquitous in today’s novel machine learning models [1, 16, 31], within one clock cycle, and CIM has been leveraged to accelerate several operation-and data-intensive workloads such as vector symbolic…”
Lightweight CNNs for Advanced Bird Species Recognition on the Edge
Berenguer-Agullo, A., Rodriguez-Juan, J., Ortiz-Pérez, D., & García‐Rodríguez, J. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-61137-7_10 · Cited by 2
Exploring Edge AI Inference in Heterogeneous Environments: Requirements, Challenges, and Solutions
Morabito, R., & Chiang, M. (2024) · Internet of things · doi:10.1007/978-3-031-58388-9_2 · Cited by 7
Edge Detection Algorithm for Urban Road Images Based on Deep Learning
Zhou, M., & Zhang, L. (2024) · International Conference on Distributed Computing and Electrical Circuits and Electronics (ICDCECE) · doi:10.1109/icdcece60827.2024.10548328 · Cited by 2
“Convolutional neural networks are frequently used in deep learning techniques for image processing, exhibiting the capacity to automatically extract features from images and accurately record information about road edges [3–4].”
BackgroundMEC Multi-Objective Task Offloading Algorithm for Joint Energy and Latency Optimization
Jin, W., Liu, G., & Gu, H. (2024) · IEEE International Conference on Big Data Security on Cloud, IEEE International Conference on High Performance and Smart Computing, and IEEE International Conference on Intelligent Data and Security (BigDataSecurity/HPSC/IDS) · doi:10.1109/hpsc62738.2024.00015 · Cited by 4
“Additionally, researchers are also investigating the trade-off between the benefits of offloading [15], such as improved performance and energy efficiency, and the overhead costs associated with offloading [16], such as communication and data management overhead [17].”
BackgroundCollaborative Inference for Deep Neural Networks in Edge Environments
Liu, M., Gu, Y., Dong, S., Wei, L., Liu, K., Yan, Y., Song, Y., Cheng, H., Tang, L., & Zhang, S. (2024) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2024.07.003 · Cited by 2
Experimental test-bed for Computation Offloading for Cooperative Inference on Edge Devices
Bovee, N., Piccolo, S., Ho, S.-S., & Wang, N. (2023) · ACM/IEEE Symposium on Edge Computing (SEC) · doi:10.1145/3583740.3626814 · Cited by 4
“More discussions of offloading approaches can be found in[3][6] (and herein).”
BackgroundCost-Sensitive Road Obstacle Detection for Low-Cost Autonomous Vehicles
Su, K., Zhao, Q., Tomioka, Y., & Liu, Y. (2024) · IEEE International Conference on Mobile Cloud Computing, Services, and Engineering (MobileCloud) · doi:10.1109/mobilecloud62079.2024.00011 · Cited by 2
“However, these mobile devices often have limited battery, computational resources and form factor, which make it challenging to run complex algorithms on it [6].”
BackgroundRen, L., Li, X., Ma, H., Zhang, G., Huang, S. M., Chen, K., Wang, X., & Yue, W. (2024) · Advances in Mechanical Engineering · doi:10.1177/16878132241281470 · Cited by 2
“11 So, reducing complexity and improving efficiency of the model are of great significance to achieve real-time and accurate bearing fault diagnosis on the edge.”
Balancing Energy Preservation and Performance in Energy-Harvesting Sensor Networks
Hribar, J., Shinkuma, R., Akiyama, K., Iosifidis, G., & Dusparić, I. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3469539 · Cited by 2
Performance Analysis of Image Classification between Edge and Cloud Computing
Vechprasit, N., Monsakul, A., & Boonsieng, P. (2024) · International Symposium on Parallel Computing and Distributed Systems (PCDS) · doi:10.1109/pcds61776.2024.10743722 · Cited by 2
“Examples of edge computing applications are Computer vision, natural language processing (NLP), network functions, Internet of Things (IoT), augmented reality (AR), and virtual reality (VR) [4].”
BackgroundPulgarín-Ospina, C. C., Launet, L., Colomer, A., & Naranjo, V. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.09.443 · Cited by 3
A cosine similarity-based token subsampling method for vision transformer in cloud computing
Li, Q., Kaneko, H., & Meng, L. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10718-w · Cited by 3
“However, network-based solutions face two challenges [11]: (1) Latency : Since computation offloading is achieved over the network, transmission latency must be considered in addition to DNNs inference latency.”
Helmy, M., Khial, N., Yaacoub, E. E., & Mohamed, A. M. S. (2024) · IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT) · doi:10.1109/gcaiot63427.2024.10833575 · Cited by 2
“These applications include monitoring and diagnosis tasks in Industrial IoT (IIoT) [1]–[4], real-time video analytics, autonomous driving, smart home, and smart healthcare applications [5], [6].”
Edge-Based Machine Learning for Immediate Botnet Detection and Response in IoT Networks
Anchitaalagammai, J. V., Kavitha, S., Murali, S., Shifana, A., & Boomika, A. (2024) · International Conference on Sustainable Communication Networks and Application (ICSCNA) · doi:10.1109/icscna63714.2024.10864079 · Cited by 2
Joint DNN Partition and Thread Allocation Optimization for Energy-Harvesting MEC Systems
Shi, Y., Li, L., Zeng, Y. W., Cong, P., & Zhou, J. (2025) · Design, Automation, and Test in Europe · doi:10.23919/date64628.2025.10993274 · Cited by 2
“Deep neural networks (DNNs) have seen widespread application across numerous fields, including computer vision, nat-ural language processing, and robotics [1].”
MicroFaaS: Adaptive serverless computing for Internet of Things
Krolik, O., & Szydło, T. (2025) · Future Generation Computer Systems · doi:10.1016/j.future.2025.107914 · Cited by 8
Araujo, S. D. C. S., Goh, M. K. O., Deshpande, U. U., Deshpande, S., Avalappa, M. G., Amasi, Y., Patil, S., Bhat, S., & Karigoudar, S. (2025) · Frontiers in Robotics and AI · doi:10.3389/frobt.2025.1680285 · Cited by 5
“To overcome these challenges, Edge AI has emerged as a more suitable solution that enables neural networks to be run locally on embedded devices, thereby improving responsiveness, data privacy, and resilience in environments with limited internet access (Chen and Ran, 2019; Li et al., 2019).”
Distributing deep learning inference on edge devices
Gunarathne, B., Prabhath, C., Perera, V., & Gunasekara, K. (2020) · ACM International Conference on emerging Networking EXperiments and Technologies (CoNEXT) · doi:10.1145/3386367.3431666 · Cited by 2
“Even though it does not require huge computational power compared to training, executing inference tasks in resource constrained edge devices is still a challenging task [1].”
BackgroundQoS Optimization of DNN Serving Systems Based on Per-Request Latency Characteristics
Zhang, J., Zhang, W., Pu, L., & Xu, J. (2020) · International Conference on Mobility, Sensing and Networking (MSN) · doi:10.1109/msn50589.2020.00064 · Cited by 2
“Compared with the cloud, advantages of edge computing for ML inference include lower latency, higher scalability and enhanced protection of privacy [12].”
BackgroundAI-edge based voice responsive smart headphone for user context-awarenes
Varun, B. V., M, K. S., & REDDY, G. (2020) · IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT) · doi:10.1109/conecct50063.2020.9198484 · Cited by 2
“Many related works in the areas of deep learning and edge computing are investigated and a comprehensive review is given in [9].”
BackgroundXuan, Z., Wei, G., Ni, Z., & Zhang, J. (2021) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-67720-6_38 · Cited by 3
Natural Language Understanding (NLU) on the Edge
Crausaz, N., Casas, J., Daher, K., Khaled, O. A., & Mugellini, E. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-74009-2_6 · Cited by 3
ISLSTM: An Intelligent Scheduling Algorithm for Internet of Things
Wu, F. Y., Musselwhite, J., Lu, S., Patel, R. V., Zuo, Q., & Dava, S. R. (2021) · Transactions on computational science and computational intelligence · doi:10.1007/978-3-030-71017-0_46 · Cited by 3
Learning-Based Fast Decision for Task Execution in Next Generation Wireless Networks
Atan, B., Çalık, N., Başaran, S. T., Başaran, M., & Durak-Ata, L. (2021) · doi:10.1109/ict52184.2021.9511542 · Cited by 2
Exploring Edge Computing for Gait Recognition
Alvarez, I. R. T., Sahonero-Alvarez, G., Menacho, C., & Suarez, J. (2021) · International Conference on Bio-engineering for Smart Technologies (BioSMART) · doi:10.1109/biosmart54244.2021.9677840 · Cited by 3
Enabling Deep Reinforcement Learning on Energy Constrained Devices at the Edge of the Network
Hribar, J., & Dusparić, I. (2022) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc51071.2022.9771901 · Cited by 5
“An alternative solution is to perform training on another more resource-rich device, e.g., cloudlet server [3], and periodically transmit the ANN to the embedded device.”
ASTC: An Adaptive Gradient Compression Scheme for Communication-Efficient Edge Computing
Wu, J., Mao, Y., & Xu, X. (2021) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc-dss-smartcity-dependsys53884.2021.00142 · Cited by 2
Ma, Y., Song, Q., Hu, M., & Zhu, X. (2022) · Neural Processing Letters · doi:10.1007/s11063-022-10951-1 · Cited by 3
CoBAAF: Controlled Bayesian Air Aggregation Federated Learning from Heterogeneous Data
Gafni, T., Cohen, K., & Eldar, Y. C. (2022) · Allerton Conference on Communication, Control, and Computing · doi:10.1109/allerton49937.2022.9929426 · Cited by 2
“These difficulties can be tackled by exploiting the increased computational power of mobile devices via mobile edge computing [2], in which training and inference is performed directly at network edges without having to share the raw data.”
BackgroundC-NMT: A Collaborative Inference Framework for Neural Machine Translation
Chen, Y., Chiaro, R., Maciiy, E., Poncino, M., & Pagliari, D. J. (2022) · IEEE International Symposium on Circuits and Systems proceedings · doi:10.1109/iscas48785.2022.9937603 · Cited by 2
“devices, research and industry are increasingly resorting to Collaborative Inference (CI) [2]–[4] a paradigm that combines edge and cloud computing, in an attempt to improve performance and energy efficiency.”
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.