Wireless Network Intelligence at the Edge
Open accessThe DOI matches its Crossref record; 205 of the 224 references it cites were found in a registry or an index, and 6 are not checked yet.
Abstract
Fueled by the availability of more data and computing power, recent breakthroughs in cloud-based machine learning (ML) have transformed every aspect of our lives from face recognition and medical diagnosis to natural language processing. However, classical ML exerts severe demands in terms of energy, memory, and computing resources, limiting their adoption for resource-constrained edge devices. The new breed of intelligent devices and high-stake applications (drones, augmented/virtual reality, autonomous systems, and so on) requires a novel paradigm change calling for distributed, low-latency and reliable ML at the wireless network edge (referred to as edge ML). In edge ML, training data are unevenly distributed over a large number of edge nodes, which have access to a tiny fraction of the data. Moreover, training and inference are carried out collectively over wireless links, where edge devices communicate and exchange their learned models (not their private data). In a first of its kind, this article explores the key building blocks of edge ML, different neural network architectural splits and their inherent tradeoffs, as well as theoretical and technical enablers stemming from a wide range of mathematical disciplines. Finally, several case studies pertaining to various high-stake applications are presented to demonstrate the effectiveness of edge ML in unlocking the full potential of 5G and beyond.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Examples of adversarial attacks include data poisoning [69, 319], model update poisoning [44, 67], and model evasion attacks [441, 69, 211].”
From Advances and Open Problems in Federated Learning (2021) · cites this paper as [211]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“To cope with this, the vanilla RNN’s hidden layer can be replaced with a long short-term memory (LSTM) unit [74].”
BackgroundElements of Information Theory
Cover, T. M., & Thomas, J. A. (2001) · Wiley eBooks · doi:10.1002/0471200611 · Cited by 36,808
(2014) · Cited by 33,419
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545 · cited 5×
“GRUs, a gating mechanism in RNNs, are commonly used for modeling speech signals and musics.”
BackgroundInfluentialMultilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728 · cited 29×
“Here, n is the sample complexity to satisfy a target generalization error with a target reliability 1 − ε. PAC Framework Applications: (a) PAC-VC Bound: If the hypothesis space H is infinite, e.g., in deep NNs or non-parametric models such as GP, one can derive the GE using the VapnikChervonenkis (VC) dimension VC(H).”
BackgroundInfluentialCommunication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215 · cited 4×
“FL has been shown to improve communication efficiency by MSI quantization [30], adjusting the MSI update period [28], and optimizing devices’ scheduling policy [31].”
BackgroundMethodInfluentialDistilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
Approximation by superpositions of a sigmoidal function
Cybenko, G. (1989) · Mathematics of Control, Signals, and Systems · doi:10.1007/bf02551274 · Cited by 13,883 · cited 1×
“The proof is provided for shallow NNs [83], [84] and recently for deep NNs [85].”
BackgroundFoundations of statistical natural language processing
Manning, C. D., & Schütze, H. (1999) · Cited by 9,816
Playing Atari with Deep Reinforcement Learning
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Riedmiller, M. (2013) · arXiv · doi:10.48550/arxiv.1312.5602 · Cited by 9,471 · cited 1×
“To illustrate its effectiveness, consider the Atari gaming environment [190] whose output action dimension is only {up, down, left, right}, whereas the input state dimension is the entire pixels per frame.”
Research works printed but not linked: 30
- 2018, Apple iPhone Xs Max
- 2018, Snapdragon 845 Mobile Platform
- 2018, Comparison Chart
- oulu, 2018, 6G Flagship
- 2018, Cloud TPU
- panda, 2018, RDMA-Based Networking Technologies and Middleware for Next-Generation Clusters and Data Centers
- 2018, Architecture Specification
- 2016, Feasibility Study on New Services and Markets Technology Enablers Release-14
- 2017, Study on New Radio Access Technology Physical Layer Aspects Release-14
- 2018, Study on Scenarios and Requirements for Next Generation Access Technologies Release 14
- iwabuchi, 2018, Field experiments on 5G ultra-reliable low-latency communication (URLLC), NTT DoCoMo Tech J, 20, 14
- 2017, Minimum Requirements Related to Technical Performance for IMT-2020 Radio Interface(s)
- 2018, Google Pixel 3 XL
- 10.1109/glocom.2016.7842367 · doi:10.1109/glocom.2016.7842367
- 2016, Recommendations for NGMN KPIs and Requirements for 5G
- briman, 2018, Another Look at Alphago vs Lee Sedol The Power Angle
- goodfellow, 2016, Deep Learning
- 2018, Service Requirements for the 5G System Stage 1 Release-14
- chaudhari, 2017, Entropy-SGD: Biasing gradient descent into wide valleys, Proc ICLR, 1
- vepakomma, 2019, Reducing leakage in distributed deep learning for sensitive health data, Proc ICLR, 1
- nakamoto, 2018, Bitcoin A Peer-to-Peer Electronic Cash System
- 2017, Coverage Analysis of LTE-M Category-M1
- metz, 2018, Machine Learning Invades the Real World on Internet Balloons
- weisstein, 2018, Fractional Chromatic Number
- 2015, IMT vision—Framework and overall objectives of the future development of IMT for 2020 and beyond
- 2017, Study on New Radio Access Technology Radio Access Architecture and Interfaces Release-14
- elgabli, 2019, Communication-efficient decentralized machine learning framework for 5G and beyond, Proc Globecom, 1
- 2018, Intel Skylake X
- 2018, Intel SSD DC P3700 Review
- 2017, Augmented and Virtual Reality The First Wave of 5G Killer Apps
Cited by
Items 501–600 of 702
Towards Energy-Efficient Intelligent Edge Computing
Afachao, K., & Abu-Mahfouz, A. M. I. (2023) · International Conference on Electrical, Computer and Energy Technologies (ICECET) · doi:10.1109/icecet58911.2023.10389568 · Cited by 3
“The algorithm used to run this continuous iteration is called the iteration algorithm [19], [20].”
MethodTowards Dynamic Real-Time Latency Bounds in 5G Communication
Maile, L., Peeck, J., Nota, A., & Saidi, S. (2024) · IEEE International Symposium on Industrial Embedded Systems (SIES) · doi:10.1109/sies62473.2024.10768011 · Cited by 3
“Existing work on dynamic contexts often leverages machine learning for predicting channels, traffic, states, and other performance indicators, see [42] for an overview.”
Online Auction for Federal Learning Client Selection in IoV
Cui, Y., Wang, P., Wu, D., He, P., Wang, R., Yan, M., & Yang, L. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3561941 · Cited by 3
“Due to the unstable state of the wireless channel, the probability of packet errors during transmission is greatly increased and the limited bandwidth also restricts the number of vehicle clients participating in FL [41].”
Uemori, S., Okura, R., Koda, Y., & Harada, H. (2025) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc61545.2025.10978776 · Cited by 3
“This fact highly limits the applicability of the sidelink communication because in the 6G era, a huger volume of data, such as a sensor data [3] and machine learning models [4], will be exchanged among vehicles or personal devices.”
DRL-based Federated Learning Node Selection Algorithm for Mobile Edge Networks
Huo, Y., Song, C., Zhang, J., & Tan, C. (2022) · IEEE International Conference on Advanced Infocomm Technology · doi:10.1109/icait56197.2022.9862659 · Cited by 3
“To address both issues, federated edge learning (FEEL) [2] – [4] has been recently proposed by combining federated learning (FL) [5], a specific distributed training framework, with the mobile edge computing (MEC) [6].”
BackgroundKI-Kanban-Behälter: Mobile, dezentrale Logistikdatenerfassung mittels Edge-ML
Rokoss, A., Popkes, L., Kramer, K. J., Green, T., & Schmidt, M. (2023) · Zeitschrift für wirtschaftlichen Fabrikbetrieb · doi:10.1515/zwf-2023-1004 · Cited by 3
Energy-Efficient Mutual Learning Over D2D Communications
Yin, R., Xiao, L., Chen, C., Chen, X., & Wu, C. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3299732 · Cited by 3
A Communication-Efficient Machine Learning Framework for the Internet of Vehicles
Ghimire, B., & Rawat, D. B. (2024) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2024.3508776 · Cited by 3
“Numerous studies have examined wireless factors that could influence the communication performance, such as those out-lined in [21], [22], [23], [24].”
System Level Knowledge Representation for Edge Intelligence
Maio, P. D. (2022) · Internet of things · doi:10.1007/978-3-030-80821-1_12 · Cited by 3
Resource Allocation in Satellite Networks—From Physical to Virtualized Network Functions
Davoli, F., & Marchese, M. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-030-87049-2_19 · Cited by 3
Sun, D., Zhao, J., Chen, B., Wu, H., & Wu, J. X. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3194535 · Cited by 3
“[33] divided distributed machine learning into data split and model split.”
A Low Complexity Approximation of Gradient Descent for Learning over Single and Multi-Agent Systems
Nassralla, M. H., Akl, N., Mohamed, A. M. S., & Dawy, Z. (2023) · IEEE International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob) · doi:10.1109/wimob58348.2023.10187884 · Cited by 3
Ultra-Low-Latency Feature Transmission for Edge Inference
Zeng, Q., Wang, Z., Zhou, Y., Hai, W., Yang, L., & Huang, K. (2024) · Globecom · doi:10.1109/globecom52923.2024.10901482 · Cited by 3
“This spread of computing from cloud to edge brings the benefits of streamlined processing of mobile data, protection of user privacy, relieved network traffic, and provisioning of ultra-low-latency access [2].”
Generative Policies for Coalition Systems - A Symbolic Learning Framework
Bertino, E., White, G., Lobo, J., Ingham, J., Cirincione, G. H., Russo, A. M., Law, M., Calo, S. B., Manotas, I., Verma, D. C., et al. (2019) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs.2019.00158 · Cited by 3
“sharing insights among different Government agencies [35], distributed electronic health records [36], machine translation [37], and intelligence in wireless networks [38].”
BackgroundStudy of Efficacious use of Blockchain in 6G Technology-Path for the Future
Voleti, R., & Noida, K. I. G. (2020) · International Journal of Engineering Research and · doi:10.17577/ijertv9is060707 · Cited by 3
“deliberated on different feasible uses of MBBLL, mBBMT, mLLMT [23].”
MethodChoi, J., Park, J., & Pokhrel, S. R. (2021) · Journal of Communications and Networks · doi:10.23919/jcn.2020.000029 · Cited by 3
Self-citationContent-driven Joint Resource Allocation Based on Vehicle-edge Synergy in Vehicular Networks
Zhu, X., Liu, F., Zeng, Z., Guo, C., & Chen, J. (2021) · IEEE Wireless Communications and Networking Conference Workshops (WCNCW) · doi:10.1109/wcncw49093.2021.9420007 · Cited by 3
“As a representative technology in the field of artifi-cial intelligence, deep learning has benefited from advances in algorithms, computing power, and data sets, which has been widely used in various computer vision applications [1].”
MethodA Family of Hybrid Federated and Centralized Learning Architectures in Machine Learning.
Elbir, A. M., & Çöleri, S. (2021) · Open Repository and Bibliography (University of Luxembourg) · Cited by 3
BER-Aware Dynamic Resource Management for Edge-Assisted Goal-Oriented Communications
Binucci, F., & Banelli, P. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10096653 · Cited by 3
“Edge Learning (EL) is an emerging paradigm of 5G/6G networks [1, 2, 3] that, moving computations closer to the network edges, overcomes the limited capabilities of wireless connected UEs, by offloading their computations to Edge Servers (ESs), and suffering moderate latency wrt cloud-based…”
BackgroundAmini, M. H. (2024) · The Research Repository @ WVU (West Virginia University) · doi:10.33915/etd.12402 · Cited by 3
Zhang, J., Chen, E., Han, D.-J., Liu, C., & Brinton, C. G. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2502.20565 · Cited by 3
Joint Client Scheduling and Resource Allocation Under Channel Uncertainty in Federated Learning
Wadu, M. M., Samarakoon, S., & Bennis, M. (2021) · IEEE Transactions on Communications · doi:10.1109/tcomm.2021.3088528 · Cited by 2
Self-citationEnergy-Efficient Connectivity Algorithm for Directional Sensor Networks in Edge Intelligence Systems
Wu, D. M., Xu, X., Lu, C., & Mu, D. (2024) · Symmetry · doi:10.3390/sym17010020 · Cited by 2
Kumar, M. R., Vijayakamal, M., Basha, S. M. E., Swathi, V. N. V. L. S., Addepalli, L., & D., V. S. S. (2025) · International Conference on Radio Frequency Communication and Networks (RFCoN) · doi:10.1109/rfcon62306.2025.11085353 · Cited by 2
“Second, reinforcement learning is applied to dynamically optimize the resource allocation problem, but most current solutions lack the scalability and adaptability to be deployed in large scale 6G environments [11].”
Sun, J., He, D., Hou, H., Du, P., Fang, C., Zhang, C., Xu, W., Wang, D., & Huang, Y. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3637039 · Cited by 2
“The integration of cloud-edge-end architectures into CF-mMIMO systems provides a promising solution to address these limitations [28], [29].”
Toward Efficient Collaborative Inference in IIoT: A Diffusion Model and DRL-Based Approach
Chen, Y., Zhou, J., Liu, B., & Niu, X. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3669635 · Cited by 2
“Moreover, diffusion-based reinforcement learning has shown promise in wireless communications, sensor networks, and industrial AI tasks such as anomaly detection, predictive reconstruction, and fault detection [115], [116], [117], [118], [119].”
Barbosa, M. V., Machado, M. O. [., Dias, K., Bassani, H. F., & Filho, A. T. D. A. (2026) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2026.3682208 · Cited by 2
“Nevertheless, supporting such requirements inevitably increases traffic intensity and resource consumption, as more packet transmissions are required to maintain reliability guarantees [4], [6].”
WFLTree: A Spanning Tree Construction for Federated Learning in Wireless Networks
Li, S., Zheng, Y., & Zou, Y. (2023) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126623502201 · Cited by 2
Evaluation and Implementation of Landscape Aesthetics Based on Cloud and Edge Computing
Qian, S. (2023) · Journal of Combinatorial Mathematics and Combinatorial Computing · doi:10.61091/jcmcc118-13 · Cited by 2
Resource-Aware Split Federated Learning for Edge Intelligence
Arouj, A., Abdelmoniem, A. M., Alhilal, A. Y., You, L., & Wang, C. (2024) · IEEE Workshop on Machine Learning on Edge in Sensor Systems (SenSys-ML) · doi:10.1109/sensys-ml62579.2024.00008 · Cited by 2
“Therefore, Edge-to-Cloud continuum approaches has been emerging [10, 25, 29, 33, 35].”
BackgroundEmpowering e-learning approach by the use of federated edge computing
Arfaoui, N., Ksibi, A., Almujally, N. A., & Ejbali, R. (2024) · Cluster Computing · doi:10.1007/s10586-024-04567-4 · Cited by 2
Federated Learning in Edge Computing Environments: Opportunities, Challenges, and Future Directions
Shaveta, X. (2024) · International Journal of Science and Research (IJSR) · doi:10.21275/es24903163414 · Cited by 2
Chennareddy, R. K., & Sethuraman, P. (2024) · International Journal of Emerging Trends in Computer Science and Information Technology · doi:10.63282/3050-9246.ijetcsit-v5i2p116 · Cited by 2
Communication-efficient k-Means for Edge-based Machine Learning
Lu, H., He, T., Wang, S., Liu, C., Mahdavi, M., Narayanan, V., Chan, K., & Pasteris, S. (2022) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2022.3144595 · Cited by 2
Wang, Y. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/3359721 · Cited by 2
“Wireless network is a network realized by wireless communication technology [9].”
BackgroundHybrid Distributed Optimization for Learning Over Networks With Heterogeneous Agents
Nassralla, M. H., Akl, N., & Dawy, Z. (2023) · IEEE Access · doi:10.1109/access.2023.3317298 · Cited by 2
“For instance, in wireless cellular networks with cooperative and distributed learning, some mobile phones may have more computational capabilities than others, and base stations may serve as edge computing nodes with much higher capabilities than cell phones [5], [36], [37], [38].”
BackgroundHierarchical Federated Learning: The Interplay of User Mobility and Data Heterogeneity
Dong, W., Yang, H. H., Feng, C., & Sun, C. (2024) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit57864.2024.10619436 · Cited by 2
“Federated learning (FL) is an emerging paradigm of distributed machine learning that enables a large number of end users to collaboratively learn a global model without directly accessing their raw data [1]–[4].”
BackgroundAge-Aware Partial Gradient Update Strategy for Federated Learning Over the Air
Du, R., Zhu, J., Li, Z., & Yang, H. H. (2026) · International Conference on Communications · doi:10.1109/icc59461.2026.11587476 · Cited by 2
“To mitigate this issue, recent studies [2]–[5] have incorporated over-the-air (OTA) computation [6] into FL.”
Toward Holistic Integration of Computing and Wireless Networking
Chen, K., Wang, Y., Nie, Z., & Cui, Q. (2020) · IFIP advances in information and communication technology · doi:10.1007/978-3-030-43605-6_13 · Cited by 2
Sparta: Heat-Budget-Based Scheduling Framework on IoT Edge Systems
Zhang, M., Krintz, C., & Wolski, R. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-96504-4_2 · Cited by 2
Sobh, T. S., & Khalil, A. H. (2022) · Recent Advances in Computer Science and Communications · doi:10.2174/2666255815666220513100257 · Cited by 2
A Framework for Named Networking on Edge AI
Flores, F. K., & Peradilla, M. S. (2022) · International Conference on Ubiquitous and Future Networks · doi:10.1109/icufn55119.2022.9829714 · Cited by 2
“The main difference however is that while NDN focuses of name resolution or lookup, NFN focuses on the expression or processing of the data [5].”
BackgroundUnderstanding Uncertainty of Edge Computing: New Principle and Design Approach
Seo, S., Ko, S., Kook, S., & Kim, S. (2022) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2022-spring54318.2022.9860481 · Cited by 2
“he edge, ranging from traditional tasks with deterministic results to tasks that utilize the recent advances in machine learning (ML) and related developments of artificial intelligence (AI) solutions [2]. The reason behind this is that AI solutions, especially deep neural networks (DNN) models, strongly embody the spe…”
BackgroundAdaptive Gradient Methods For Over-the-Air Federated Learning
Wang, C., Chen, Z., Yang, H. H., & Παππάς, Ν. (2023) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc53906.2023.10304465 · Cited by 2
BayGO: Decentralized Bayesian Learning and Information-Aware Graph Optimization Framework
AlShammari, T., Weeraddana, P. C., & Bennis, M. (2024) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2024.3387277 · Cited by 2
“The latter is usually referred to as multi-agent decentralized learning (MADL) [4], [5].”
BackgroundSelf-citationLatency Guarantee for Ubiquitous Intelligence in 6G: A Network Calculus ApproachPreprint
Zhang, L., Wang, Q., Dong, P., Wei, Y., & Mei, J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2205.03115 · Cited by 2
“Training delay is captured by loss or weight convergence, while inference delay refers to the computing and memory access delay [14].”
BackgroundCommunication-Computation Efficient Federated Learning over Wireless Networks
Mahmoudi, A. (2023) · DiVA (Digitala Vetenskapliga Arkivet) · Cited by 2
Parametric-Sensitivity Aware Retransmission for Efficient AI DownloadingPreprint
Zhou, Y., Zeng, Q., & Huang, K. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.13607 · Cited by 2
“This dependency can be problematic for mission-critical applications that require real-time responses, such as augmented/virtual reality (AR/VR) [8] or remote healthcare [9], particularly under poor wireless channel conditions.”
Delayed Random Partial Gradient Averaging for Federated Learning
Hu, X. (2023) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc53906.2023.10304494 · Cited by 1
“Federated learning (FL) [1]–[3] is a privacy-preserving machine learning paradigm that enables multiple clients to jointly train a global model without sharing their local data.”
BackgroundSemantic Communications and Networking
Yun, W. J., Park, S., Lee, R., Park, J., Ko, Y., & Kim, J. (2023) · Signals and communication technology · doi:10.1007/978-3-031-37920-8_29 · Cited by 1
Self-citationD2D-assisted two-stage model aggregation scheme based on over-the-air computation
ZHANG, R., Deng, N., Wei, H., Xing, C., & Nan, Z. H. A. O. (2024) · Scientia Sinica Informationis · doi:10.1360/ssi-2023-0402 · Cited by 1
Convergence Analysis of Semi-Federated Learning with Non-IID Data
Ni, W., Han, J., & Qin, Z. (2024) · IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW) · doi:10.1109/icasspw62465.2024.10627110 · Cited by 1
“However, various types of IoT devices (e.g., temperature sensor, smart watch, and mobile phone) usually have different computing capabilities [4,5].”
BackgroundHybridCom: Improve Federated Learning Efficiency on Unstable Data
Li, J., Zhang, Y., Li, Y., Gong, X., & Wang, W. (2024) · International Conference on Communications · doi:10.1109/icc51166.2024.10622354 · Cited by 1
“Federated learning(FL) has attracted significant attention as a promising approach to collaborative learning without the need for sharing private data [1], [2].”
BackgroundMadugula, S. C. (2025) · International Journal of Scientific Research in Computer Science Engineering and Information Technology · doi:10.32628/cseit251112104 · Cited by 1
RS-IML: Federated Intrinsic Mask Learning on Remote Sensing Image Interpretation
Ye, H., Xie, W., Zhang, X., Lü, Y., Li, Y., & Fang, L. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3587952 · Cited by 1
“They have a limited storage size [15], [16], [17] and power budget, while the ground center node is not sustainably accessible [17], [18], as show in Fig. over-parameterization, leading to inefficiency and excessive complexity when deployed on edge devices.”
Mobility -Aware Resource Allocation in Edge Networks for Smart Neighborhoods
Pallantla, S., Haritha, D., & Chilukuri, S. (2025) · International Journal of Electronics and Communication Engineering · doi:10.14445/23488549/ijece-v12i8p117 · Cited by 1
Adaptive Asynchronous Federated Learning with Convolutional Autoencoders in Heterogeneous Systems
Kim, J., & Guo, W. (2025) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case58245.2025.11163956 · Cited by 1
“Park et al. [11] demonstrated the importance of intelligent edge computing in wireless networks, including unsupervised federated learning approaches for mobile sensor data analysis.”
Edge Intelligence: Unique Machine Learning Strategies for Enhancing Real-Time IoT Data Processing
Pal, M. K., Dey, R., Mahajan, R. A., Khan, M., Syed, A. A., & Karimullah, S. (2025) · IEEE International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN) · doi:10.1109/qpain66474.2025.11171994 · Cited by 1
“Zhou et al. [9] and D. Li et al. [15] have also considered energy-efficient methods and adaptive resource management that maintain large-scale IoT deployments.”
InfluentialKondratenko, Y., Кірпічніков, Ю. А., Романюк, А., KRYVORUCHKO, I., & Onofriichuk, O. (2025) · Informatica · doi:10.31449/inf.v49i37.8682 · Cited by 1
Self-Healing Telecom Networks with AI-Driven Autonomous Operations (AIOps)
Averineni, A. (2026) · International Journal of Computational and Experimental Science and Engineering · doi:10.22399/ijcesen.4947 · Cited by 1
“Local processing of data at network edges reduces bandwidth consumption for telemetry transmission; besides, it addresses privacy concerns since sensitive operational data stays within operator control and is not transmitted to external cloud platforms [5].”
Adaptable Variational Information Bottleneck for Task-Oriented Edge Inference
Tarimo, E., Xing, H., Xu, L., Peng, J., & Feng, L. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3681230 · Cited by 1
“Independent encoding of features without redundancy suppression and uniform rate allocation across devices may lead to excessive bandwidth consumption and redundant transmissions [18], [70].”
Goncharov, D. (2026) · International Russian Smart Industry Conference (SmartIndustryCon) · doi:10.1109/smartindustrycon68821.2026.11492981 · Cited by 1
“…computational system components, assessing the feasibility of specified performance parameters, and optimizing the architecture of a distributed machine vision system in the context of Industry 4.0, taking into account modern approaches to organizing edge computing and adaptive systems [6, 7, 14].”
InfluentialKim, J.-M., Guo, Y. B., Ezzat, A. A., & Guo, W. (2026) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2026.05.005 · Cited by 1
Vijayakumar, S. (2026) · IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE) · doi:10.1109/iscaie68866.2026.11576449 · Cited by 1
“This multi-model approach lets the system represent both changes over time and sudden departures from expected performance [11],[12].”
Okura, R., Koda, Y., & Harada, H. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3710761 · Cited by 1
“As collaborative intelligence becomes more relevant, the demand for the wireless exchange of ML models among UEs is expected to grow [7].”
Batsios, V. D., & Angelis, C. T. (2026) · Future Internet · doi:10.3390/fi18080416 · Cited by 1
“…[3,7,19]: (1) use at least one non-trivial vision dataset before framework selection; (2) budget scheduling windows from measured T wall including variance across seeds; and (3) plan uplink capacity using C total from Equation (6) before applying bandwidth-limited or mMTC profiles [1,8,19].”
Mastoi, Q.-U.-A., Phung, K., & Morley, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-35390-0_11 · Cited by 1
Waheed, H., Abro, G. E. M., Memon, S. A., & Saeed, N. (2026) · Scientific Reports · doi:10.1038/s41598-026-68713-1 · Cited by 1
Spatial-Temporal Graph Neural Network Enabled Security Situation Prediction for 6G Edge Networks
Xu, H., Wang, W., Shao, X., Zhou, B., Liu, Y., Lu, X., & Wang, Z. (2026) · Chinese Journal of Electronics · doi:10.23919/cje.2025.00.489 · Cited by 1
Deep Learning Tasks Processing in Fog-RAN
Hua, S., Yang, X., Yang, K., Yin, G., Shi, Y., & Wang, H. (2019) · IEEE Vehicular Technology Conference · doi:10.1109/vtcfall.2019.8891505 · Cited by 1
“A promising approach is to perform intelligent tasks at network edges instead of sending all data and models to the centralized cloud center, which is termed as edge machine learning (edgeML) [3].”
BackgroundService Chaining Offloading Decision in the EdgeAI: A Deep Reinforcement Learning Approach
Lee, M., & Hong, C. S. (2020) · Asia-Pacific Network Operations and Management Symposium (APNOMS) · doi:10.23919/apnoms50412.2020.9237048 · Cited by 1
“There are several researches related to the offloading methods for autonomous vehicle system with edge computing model[3][4].”
BackgroundBožanić, M., & Sinha, S. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-3-030-69273-5_8 · Cited by 1
Communication-efficient k-Means for Edge-based Machine Learning
Lu, H., He, T., Wang, S., Liu, C., Mahdavi, M., Narayanan, V., Chan, K., & Pasteris, S. (2020) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/icdcs47774.2020.00062 · Cited by 1
“The need of communications arises in the emerging application scenario of edge-based machine learning [8], where mobile/wireless devices collect the raw data and transmit them to nearby edge servers for processing.”
BackgroundEdge Analytics and Deep Learning for Sustainable Development
Singh, S. K., Chakraborty, S., & Soodan, V. (2021) · EAI/Springer Innovations in Communication and Computing · doi:10.1007/978-3-030-70183-3_10 · Cited by 1
Device Selection of Distributed Primal-Dual Algorithms Over Wireless Networks
Yang, Z., Huang, C., Xu, H., Xu, W., & Cao, Y. (2021) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2021-fall52928.2021.9625364 · Cited by 1
Resource Optimization for Wireless Federated Learning
Hong, C. S., Khan, L. U., Chen, M., Chen, D., Saad, W., & Han, Z. (2021) · Wireless networks · doi:10.1007/978-981-16-4963-9_3 · Cited by 1
Bagus, M. Y., Murad, F. A., Elisa, R., & Hermawan, I. (2022) · International Conference of Computer and Informatics Engineering (IC2IE) · doi:10.1109/ic2ie56416.2022.9970095 · Cited by 1
“The power spectrum shapes of the two devices are the same, so the power spectral density of the DSSS signal is 1/N of the un-spread sign [10], the instantaneous rate may frequently fluctuate due to poor wireless channel conditions, hindering inter-device communication [11].”
BackgroundYoshida, N., Nishio, T., Yamamoto, K., & Morikura, M. (2023) · Engineering cyber-physical systems and critical infrastructures · doi:10.1007/978-3-031-29301-6_11 · Cited by 1
Albaseer, A. M., Abdallah, M. M., & Al‐Fuqaha, A. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10278872 · Cited by 1
“Mobile Edge Computing (MEC) can utilize the unprecedented capabilities of these devices to perform complex streaming tasks and provide intelligent services [2].”
BackgroundFederated Learning with Partial Gradients Over-the-Air
Wang, W., Chen, Z., Παππάς, Ν., & Yang, H. H. (2023) · IEEE International Conference on Sensing, Communication, and Networking (SECON) · doi:10.1109/secon58729.2023.10287423 · Cited by 1
“Federated learning (FL) is a distributed learning paradigm emerging from the intersection of artificial intelligence and edge computing, aiming to provide intelligent services to multiple clients in a privacy-preserving way [1]–[3].”
BackgroundIntelliot: a smart IoT environment
Masserov, D., & Masserov, D. A. (2023) · Russian journal of resources conservation and recycling · doi:10.15862/02inor223 · Cited by 1
Effect of 6G Network in our Environment
Pawar, A. J., & Khan, A. (2024) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-15213 · Cited by 1
Clustering-Based Federated Learning for Heterogeneous IoT Data
Li, S.-M., Wei, L., Zhang, W., & Wu, X. (2023) · IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) · doi:10.1109/ithings-greencom-cpscom-smartdata-cybermatics60724.2023.00051 · Cited by 1
“Traditional centralized Machine Learning (ML) needs to aggregate large amounts of data from multiple IoT devices to the server to train complex Deep Learning (DL) models [6], [7].”
BackgroundIntelligent Edge: The Intersection of Artificial Intelligence and Digital Communication—A Survey
Samara, G., Daoud, E. A., Alazaidah, R., Qasem, M. H., Aljaidi, M., Alzyoud, M. S., & Nasseif, H. (2024) · Studies in systems, decision and control · doi:10.1007/978-3-031-56586-1_73 · Cited by 1
Xu, Z., Kim, D. I., & Woo, S. S. (2024) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc62082.2024.10826855 · Cited by 1
Federated Meta Continual Learning for Efficient and Autonomous Edge Inference
Li, B., Ho, S., Qu, Y., Xu, C., Luan, T. H., & Gao, L. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-1548-3_17 · Cited by 1
Asynchronous and Flexible Federated Learning for COVID-19 Detection from Chest X-Ray Images
Elhajjej, M. H., Said, S., Arfaoui, N., & Ejbali, R. (2025) · Journal of Advanced Computational Intelligence and Intelligent Informatics · doi:10.20965/jaciii.2025.p0857 · Cited by 1
Wireless Resource Efficient Distributed Learning with Deep Joint Source-Channel Coding
Matsumura, I., & Suto, K. (2024) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshp64532.2024.11100602 · Cited by 1
“At the same time, artificial intelligence (AI) is also transited from cloud AI to edge AI [1], [2].”
The Race for Future Wireless Internet and Socio-Economic AspectsPreprint
Gupta, S. (2022) · doi:10.36227/techrxiv.20131475.v1 · Cited by 1
Situational Awareness for Industry 5.0 and Mobile Robotics: A ReviewPreprint
Höyhtyä, M. (2023) · doi:10.36227/techrxiv.22602028 · Cited by 1
Koda, Y., Okura, R., & Harada, H. (2024) · doi:10.36227/techrxiv.173377556.60268214/v1 · Cited by 1
Visual Data-Driven Millimeter Wave Communication Systems
Koda, Y. (2021) · Institutional Repositories DataBase (IRDB) · doi:10.14989/doctor.k23329 · Cited by 1
Design and Optimization of 5G and Beyond Hybrid Communication Systems
Torkzaban, N. (2023) · University Libraries (University of Maryland) · doi:10.13016/sefk-19rz · Cited by 1
INDIRECT TASK-ORIENTED COMMUNICATION DESIGN FOR CONTROL AND DECISION MAKING IN MULTI-AGENT SYSTEMS
Mostaani, A. (2023) · Open Repository and Bibliography (University of Luxembourg) · Cited by 1
Kaur, H., Kritika, Jasmine, & Gupta, V. (2026) · Wiley eBooks · doi:10.1002/9781394370702.ch4 · Cited by 1
Distributed Learning for 5G and Beyond Network Management and Orchestration
Sana, M. (2021) · theses.fr (ABES) · doi:10.70675/0f4e2d38zaf10z472bz98caz8ad6e228b6c8 · Cited by 1
Learning from Peers at the Wireless Edge
Chakraborty, S., Mohammed, H. H., & Saha, D. (2020) · International Conference on Communication Systems & Networks (COMSNETS) · doi:10.1109/comsnets48256.2020.9027318
Hribar, J. (2020) · Arrow@dit (Dublin Institute of Technology)
Change the Pattern: Exploring Sensing-Communication in Wireless Networks
Liu, S., Yang, T., Gan, X., & Xia, M. (2020) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp49889.2020.9299708
Metadata
- Authors
- Park, J., Samarakoon, S., Bennis, M., & Debbah, M.
- Affiliations
- University of Oulu (FI)
- Université Paris-Saclay (FR)
- Venue
- Proceedings of the IEEE
- Published
- 2019-11
- Volume
- 107
- Issue
- 11
- Pages
- 2204-2239
- ISSN
- 0018-9219 (ISSN-L)
- 1558-2256
- OpenAlex
- W2904648777
- Cited by
- 92
- References
- 224
- Citations by year
- 2026: 8 · 2025: 2 · 2024: 6 · 2023: 10 · 2022: 13 · 2021: 8 · 2020: 29 · 2019: 16
- FWCI
- 9.03
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- Proceedings of the IEEE (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Figshare (submittedVersion, cc-by)
- arXiv (Cornell University)
- Funders
- Academy of Finland (294128)
- 6Genesis Flagship (318927)
- Kvantum Institute Strategic Project SAFARI
- Academy of Finland through the MISSION Project (319759)
- Artificial Intelligence for Mobile Wireless Systems AIMS project at the University of Oulu
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Computer Networks and Communications › Distributed Sensor Networks and Detection Algorithms
- Keywords
- edge machine learning, wireless networks, distributed learning, resource-constrained edge devices, 5G, federated learning, low-latency inference, autonomous systems, unmanned aerial vehicles, virtual and augmented reality
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.