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 401–500 of 702
On the Importance of Trust in Next-Generation Networked CPS Systems: An AI PerspectivePreprint
Gholami, A., Torkzaban, N., & Baras, J. S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.07853 · Cited by 9
“requires a novel paradigm change calling for distributed, low-latency and reliable ML at the network edge (referred to as edge ML [4]).”
BackgroundFederated Reinforcement Distillation with Proxy Experience MemoryPreprint
Cha, H., Park, J., Kim, H., Kim, S., & Bennis, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.06536 · Cited by 9
“Recent advances in mobile computing power has led to the emergence of intelligent autonomous systems [Park et al. , 2018, Shiri et al. , 2019], ranging from driverless cars and drones to self-controlled robots in smart factories.”
BackgroundSelf-citationMachine Learning-Based Radio Environment Maps for 4G/5G Networks
Rekkas, V. P., Sotiroudis, S. P., Zaharis, Z. D., Koudouridis, G. P., Sarigiannidis, P., Karagiannidis, G. K., Christodoulou, C. G., & Goudos, S. K. (2025) · IEEE Transactions on Antennas and Propagation · doi:10.1109/tap.2025.3607974 · Cited by 8
“In many practical scenarios, the requisite data may not be su ffi ciently comprehensive or may lack the necessary granularity, thereby impacting model performance adversely [35].”
6G Wireless Systems: Challenges and Opportunities
Saad, W. (2020) · Springer eBooks · doi:10.1007/978-3-030-58197-8_7 · Cited by 8
Federated Stochastic Gradient Descent Begets Self-Induced Momentum
Yang, H. H., Liu, Z., Fu, Y., Quek, T. Q. S., & Poor, H. V. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746995 · Cited by 8
Verma, G., Shahi, A. P., & Prakash, S. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-16-8826-3_16 · Cited by 8
Pase, F., Gündüz, D., & Zorzi, M. (2022) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit50566.2022.9834399 · Cited by 8
Cost-Efficient Sharing Algorithms for DNN Model Serving in Mobile Edge Networks
Dai, H., Wu, J., Wang, Y., Yen, J., Zhang, Y., & Xu, C. (2023) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2023.3247049 · Cited by 8
“…the foregoing issues, at present, the mainstream of DNN deployment mode in the edge is so-called In-Cloud Training and In-Edge Co-inference (ICIE), which means the model training is accomplished in the cloud while the model co-inference is conducted between the edge and mobile device [10], [14].”
BackgroundNovel Approach for Curbing Unfair Energy Consumption and Biased Model in Federated Edge Learning
Albaseer, A. M., Seid, A. M., Abdallah, M. M., Al‐Fuqaha, A., & Erbad, A. (2024) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2024.3350735 · Cited by 8
“This helps in the rapid development of solutions for more livable communities [1], [2], [3], [4], [5].”
BackgroundOptical Wireless Communications: Illuminating the Path for Cooper’s Law
Eltokhey, M. W., Bashir, M. S., Younus, O. I., Ghassemlooy, Z. F., Haas, H., Karagiannidis, G. K., Teli, S. R., Zvánovec, S., Khalighi, M., Zhang, Z. C., et al. (2026) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2026.3699489 · Cited by 8
A Short Overview of 6G V2X Communication Standards
Wang, D., Nganso, Y. N., & Schotten, H. D. (2023) · International Conference on Intelligent Communication and Networking (ICN) · doi:10.1109/icn60549.2023.10425918 · Cited by 8
“[27] [28] [29] [30].”
Model Compression by Count Sketch for Over-the-Air Stateless Federated Learning
Ahn, J.-H., Kim, G.-Y., Kim, D. H., & You, C. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3376771 · Cited by 8
Optimizing AI Service Placement and Computation Offloading in Mobile Edge Intelligence Systems
Lin, Z., Bi, S., & Zhang, Y. A. (2020) · Globecom · doi:10.1109/globecom42002.2020.9348232 · Cited by 8
“Edge intelligence (EI) [1]–[3], the integration of mobile edge computing (MEC) and artificial intelligence (AI) technologies, has recently emerged as a promising paradigm to support computationally intensive training and inference processes of AI models at the edge servers, e.g., cellular base…”
BackgroundSpatial-Temporal Learning-Based Artificial Intelligence for IT Operations in the Edge Network
Qi, Q., Shen, R., Wang, J., Sun, H., Guo, S., & Liao, J. (2021) · IEEE Network · doi:10.1109/mnet.011.2000278 · Cited by 8
“More and more emerging services such as autonomous driving, live broadcast, and industrial control are deployed on edge networks [1].”
BackgroundIntellIoT: Intelligent IoT Environments
Bröring, A., Kulkarni, V., Zirkler, A., Buschmann, P., Fysarakis, K., Mayer, S., Soret, B., Nguyen, L. D., Popovski, P., Samarakoon, S., et al. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-20936-9_5 · Cited by 8
“Next generation IoT applications require a paradigm shift from classic ML to distributed, low-latency and reliable ML at the wireless network edge [22].”
BackgroundSelf-citationOver-the-Air View-Pooling for Low-Latency Distributed Sensing
Liu, Z., Lan, Q., Kalør, A. E., Popovski, P., & Huang, K. (2023) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc53906.2023.10304546 · Cited by 8
“One is the ubiquitous deployment of artificial intelligence (AI) algorithms at the network edge, termed edge AI, to empower Internet-of-things (IoT) applications [2].”
BackgroundCommunication-Efficient Edge AI Inference Over Wireless NetworksPreprint
Yang, K., Zhou, Y., Yang, Z., & Shi, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2004.13351 · Cited by 8
“With the increase of the computing power and storage capability of edge servers (e.g., APs and base stations) and end devices (vehicles and robots), there is a trend of pushing AI engines from the cloud center to the network edge [8], [9].”
BackgroundCollaborative Learning over Wireless Networks: An Introductory OverviewPreprint
Özfatura, E., Gündüz, D., & Poor, H. V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2112.05559 · Cited by 8
“The solution to all these limitations is to bring the intelligence to the network edge by enabling wireless devices to implement learning algorithms in a distributed and collaborative manner [1], [2].”
BackgroundCano, M., Guillén, A., Tasic, I. A. B., & Villafranca, A. (2024) · International Conference on Control, Robotics and Cybernetics (CRC) · doi:10.1109/crc60659.2023.10488509 · Cited by 7
“The concept of EI refers to approaches in which data is collected, analyzed, and processed as close as possible to where it is captured in the network [1], [8], [54]–[56].”
BackgroundRobust Federated Learning Over the Air: Combating Heavy-Tailed Noise with Median Anchored Clipping
Li, J., Chen, Z., Chong, K. F. E., Das, B., Quek, T. Q. S., & Yang, H. H. (2025) · International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt) · doi:10.23919/wiopt66569.2025.11123216 · Cited by 7
Battiloro, C., Merluzzi, M., Lorenzo, P. D., & Barbarossa, S. (2022) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp43922.2022.9746891 · Cited by 7
Fully Distributed Federated Learning with Efficient Local Cooperations
Georgatos, E., Mavrokefalidis, C., & Berberidis, K. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095741 · Cited by 7
“Fueled by high data and computational power availability, Machine Learning (ML) has a transformative impact on our lives by offering high accuracy tools for tasks like natural language processing, object recognition, and medical diagnosis [1, 2, 3, 4].”
BackgroundEfficient Federated Meta‐Learning Over Multi‐Access Wireless Networks
Yue, S., & Ren, J. (2024) · Wiley eBooks · doi:10.1002/9781394180523.ch22 · Cited by 7
Ma, X., & Ding, S. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3394695 · Cited by 7
“Themodel-based optimization algorithms can be executed on a vehicular edge computing platform, which consists of multiple Service Vehicles (SeVs) with significant computational power, proxied by a local roadside unit (RSU) [45].”
BackgroundA Review and Bibliometric Analysis of the Current Studies for the 6G Networks
Salih, Q. M., Rahman, M. A., Firdaus, A., Jassim, M. R., Kahtan, H., Zain, J. M., & Ali, A. H. (2024) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2024.028132 · Cited by 7
Yang, T., Li, Q., Zhang, N., Zhao, L., & Hu, F. (2024) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2024-spring62846.2024.10683391 · Cited by 7
“However, in practice, wireless channels’ unreliability and resource limitations (e.g., bandwidth and power) can cause training errors in FL algorithms [11].”
Li, X., & Xiao, W. (2022) · Mathematical Problems in Engineering · doi:10.1155/2022/6729830 · Cited by 7
“Based on perception, the scalable multidimensional complex system formed by deep integration of computing, communication, and control is expected to develop rapidly in recent years [23].”
BackgroundRetractedAutoSF: Adaptive Distributed Model Training in Dynamic Edge Computing
Yang, L., Gan, Y., Chen, J., & Cao, J. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2023.3323456 · Cited by 7
“…environments such as vehicular networks [31], [32], drone networks [33], [34], and smart grids [35], [36] are highly dynamic and volatile, characterized by edge device mobility, unreliability network connectivity, changing network topology, and fluctuating links bandwidth [37], [38], [39], [40].”
BackgroundWireless Data Acquisition for Edge Learning: Data-Importance Aware Retransmission
Liu, D., Zhu, G., Zhang, J., & Huang, K. (2018) · Research Portal (King's College London) · doi:10.48550/arxiv.1812.02030 · Cited by 7
A Spiking Neural Network Based Auto-encoder for Anomaly Detection in Streaming Data
Stratton, P. G., Wabnitz, A., & Hamilton, T. J. (2020) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci47803.2020.9308187 · Cited by 7
“…or latency constraints, communication channels may be unreliable or open to attack, adaptation or online training may be required, privacy or security is a factor, or any number of others reasons why relying on big, remote, power-hungry and unadaptive ML models may be inappropriate [5]– [7].”
BackgroundFederated Reinforcement Distillation with Proxy Experience MemoryPreprint
Cha, H., Park, J., Kim, H., Kim, S., & Bennis, M. (2020) · doi:10.36227/techrxiv.12645497.v1 · Cited by 7
Self-citationDistributed Heteromodal Split Learning for Vision Aided mmWave Received Power PredictionPreprint
Koda, Y., Park, J., Bennis, M., Yamamoto, K., Nishio, T., & Morikura, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.08208 · Cited by 7
“Collaborative learning frameworks exemplified by FL [13], [30], [31], have recently attracted an increasing interest.”
BackgroundSelf-citationLogit Poisoning Attack in Distillation-based Federated Learning and its CountermeasuresPreprint
Yu, Y., Zhu, S., & Hu, J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2401.17746 · Cited by 7
“F EDERATED learning (FL) [1], [2], [3], [4], [5], [6] represents a paradigm shift in collaborative machine learning, enabling parallel and distributed training across multiple clients.”
BackgroundVirtual Reality Learning Environments: A Review of Support for Autonomous Learning Development
Fernández-Arias, P., del Bosque, A., & Vergara, D. (2026) · Multimodal Technologies and Interaction · doi:10.3390/mti10020018 · Cited by 6
“In addition, the application of VR in personalized environments facilitates experimentation [13], active problem solving, and the acquisition of practical skills in a safe and controlled space [21].”
InfluentialSplit Learning Meets Koopman Theory for Wireless Remote Monitoring and Prediction
Girgis, A. M., Seo, H., Park, J., Bennis, M., & Choi, J. (2021) · IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC) · doi:10.1109/pimrc50174.2021.9569357 · Cited by 6
“To fill this void, in this article we propose a novel deep learning framework for wireless remote monitoring and prediction, inspired by Koopman autoencoder [10] and split learning [11], [12].”
MethodSelf-citationLeveraging Channel Noise for Sampling and Privacy via Quantized Federated Langevin Monte Carlo
Zhang, Y., Liu, D., & Simeone, O. (2022) · IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) · doi:10.1109/spawc51304.2022.9833991 · Cited by 6
Parallel Split Learning with Global Sampling
Kohankhaki, M., Ayad, A., Barhoush, M., & Schmeink, A. (2025) · International Conference on Foundation and Large Language Models (FLLM) · doi:10.1109/fllm67465.2025.11391108 · Cited by 6
“Distributed deep learning (DDL) has emerged as a powerful paradigm in the era of the Internet of Things (IoT), addressing the challenges posed by the proliferation of resource-constrained devices and the exponential growth of data at the network edge [1]±[3].”
Nooh, S. A. (2024) · The Journal of Supercomputing · doi:10.1007/s11227-024-06503-0 · Cited by 6
Bilal, N., & Velmurugan, T. (2024) · International Journal of Communication Systems · doi:10.1002/dac.6060 · Cited by 6
“Various challenges in wireless communications and networking, such as physical layer design [9], resource allocation (RA) [10], networking [11], caching [12], and edge computing [13], have recently attracted researchers who aim to solve them using machine learning techniques.”
Data-Aided Sensing Where Communication and Sensing Meet: An Introduction
Choi, J. (2020) · IEEE Wireless Communications and Networking Conference Workshops (WCNCW) · doi:10.1109/wcncw48565.2020.9124732 · Cited by 6
“This approach can be applied to federated learning [11] [12] [13], as studied in [8].”
MethodCommunication-Efficient and Privacy-Preserving Feature-based Federated Transfer Learning
Wang, F., Gursoy, M. C., & Velipasalar, S. (2022) · Globecom · doi:10.1109/globecom48099.2022.10000612 · Cited by 6
“overall dataset is imbalanced and hence the samples with certain types of output appears much more frequently than those of other outputs, it is hard to distinguish for FL and FTL via gradient updates, and such imbalanced data distribution could significantly degrade FL performance [49], [50].”
BackgroundAdaptive ResNet Architecture for Distributed Inference in Resource-Constrained IoT Systems
Khan, F. M., Baccour, E., Erbad, A., & Hamdi, M. (2023) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc58020.2023.10182881 · Cited by 6
Alhussein, O., Wei, M., & Akhavain, A. (2023) · Globecom · doi:10.1109/globecom54140.2023.10437933 · Cited by 6
“To this paper’s context, IB can fit in semantic communications [19]–[22] and wireless-edge learning [23], [24].”
BackgroundOn Data Summarization for Machine Learning in Multi-organization Federations
Ko, B. J., Wang, S., He, T., & Conway-Jones, D. (2019) · IEEE International Conference on Smart Computing · doi:10.1109/smartcomp.2019.00030 · Cited by 6
“As discussed in [22], [23], a summary (or small subset)”
BackgroundProbabilistic Node Selection for Federated Learning with Heterogeneous Data in Mobile Edge
Wu, H., & Wang, P. (2022) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc51071.2022.9771994 · Cited by 6
“The improved data confidentiality and reduced volume of communication cost make FL one of the most promising technologies for future network intelligence [4].”
BackgroundFramework for Trustworthy AI/ML in B5G/6G
Barmpounakis, S., & Demestichas, P. (2022) · International Conference on 6G Networking (6GNet) · doi:10.1109/6gnet54646.2022.9830408 · Cited by 6
Latency Guaranteed Edge Inference via Dynamic Compression Ratio Selection
Huang, X., & Zhou, S. (2020) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc45663.2020.9120768 · Cited by 6
“…(IoT) devices at network edge [1], can enable many applications such as autonomous driving, intelligent manufacturing, environment monitoring, and etc. Emerging technology like edge learning [2][3] focuses on deploying machine learning algorithms at the wireless access network edge.”
BackgroundFedRAN: Federated Mobile Edge Computing with Differential Privacy
Gottipati, A., Stewart, A. A., Song, J., & Chen, Q. (2021) · doi:10.1145/3472735.3473392 · Cited by 6
“Previous work has focused on exploring federated deployments in IoT type networks and simulated mobile environments, utilizing low bandwidth and simulated endpoints to emulate the respective environments [5, 17–19, 21, 22].”
BackgroundChannel-Adaptive Quantization for Wireless Federated Learning
Lin, X., Liu, Y., & Chen, F. (2021) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc52777.2021.9580257 · Cited by 6
Making a Spiking Net Work: Robust brain-like unsupervised machine learningPreprint
Stratton, P. G., Wabnitz, A., Essam, C., Cheung, A., & Hamilton, T. J. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2208.01204 · Cited by 6
“numbers of free parameters and commensurately sized training datasets [3, 4], meaning that they are poorly suited for many real-world applications where the problems are not necessarily static or a priori easy to capture explicitly, where training data may be sparse or expensive to collect, high power data servers are…”
BackgroundRadio resource allocation in 5G cellular networks powered by the smart grid and renewable energies
Amine, A. E. (2019) · theses.fr (ABES) · doi:10.70675/083fe1dcz5f71z4c13za099zf303890b3d11 · Cited by 6
-, K. K. P. B. (2024) · International Journal For Multidisciplinary Research · doi:10.36948/ijfmr.2024.v06i05.29826 · Cited by 5
Personalized Federated Learning Over the Air
Li, Z., Chen, Z., Quek, T. Q. S., & Yang, H. H. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3573777 · Cited by 5
Li, M., Zhou, H., Xu, X., Zhong, Z., Quan, P., Zhu, X., Lin, Y., Lin, W., Li, X., Wang, D. D., et al. (2026) · Nature Communications · doi:10.1038/s41467-026-70586-x · Cited by 5
Distributed AI-RAN Inference Placement for Joint Radio Optimization and Edge Workload Acceleration
Mahadasu, S. S., & Rallabandi, B. R. (2025) · International Journal of AI Electronics and Nexus Energy · doi:10.64751/7ep35m50 · Cited by 5
DDPG-FL: A Reinforcement Learning Approach for Data Balancing in Federated Learning
Ouyang, B., Li, J., & Chen, X. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-3890-8_3 · Cited by 5
From Theory to Practice: Implementing Meta-Learning in 6G Wireless Infrastructure
Zeshan, A., Ouameur, M. A., Alam, M. Z., & Le, T.-A. D. (2024) · Telecom · doi:10.3390/telecom5040063 · Cited by 5
Heterogeneity-Aware Clustering and Intra-Cluster Uniform Data Sampling for Federated Learning
Chen, J., Zhang, P., Chen, J., & Lau, T. S. C. (2024) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2024.3515007 · Cited by 5
“Among these challenges, category distribution heterogeneity emerges as a critical issue of data heterogeneity [9], [10], [11].”
Adaptive Decentralized Federated Learning in Energy and Latency Constrained Wireless Networks
Yan, Z., Li, D., Sun, Q., Niyato, D. T., & Quek, T. Q. S. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3611075 · Cited by 5
Unveiling the Wireless Network Limitations in Federated Learning
Eris, M. C., Kantarcı, B., & Oktuğ, S. (2021) · IEEE International Symposium on Dynamic Spectrum Access Networks · doi:10.1109/dyspan53946.2021.9677285 · Cited by 5
MAFAT: Memory-Aware Fusing and Tiling of Neural Networks for Accelerated Edge Inference
Farley, J., & Gerstlauer, A. (2023) · IFIP advances in information and communication technology · doi:10.1007/978-3-031-34214-1_7 · Cited by 5
“Running ML applications on the edge can increase privacy, improve latency, reduce cloud communication, and require less energy [9].”
BackgroundPineda, V. G., Valencia-Arías, A., Patiño-Vanegas, J. C., Cueto, J. J. F., Arango-Botero, D. M., Coronel, Á. M. R., & Rodríguez-Correa, P. A. (2023) · Informatics · doi:10.3390/informatics10030073 · Cited by 5
Federated Graph Learning for Low Probability of Detection in Wireless Ad-Hoc Networks
Krishnan, S., Park, J., Sagar, S., Sherman, G., Campbell, B., & Choi, J. (2023) · IEEE Statistical Signal Processing Workshop (SSP) · doi:10.1109/ssp53291.2023.10208058 · Cited by 5
“Furthermore, to reduce the background communication cost that is proportional to the number of local model parameters [18], we apply a model pruning method that removes redundant model parameters while maintaining prediction accuracy [19].”
MethodSelf-citationMishra, R., & Gupta, H. P. (2023) · ACM Transactions on Sensor Networks · doi:10.1145/3629978 · Cited by 5
“Ubiquitous system has recently emerged as an attractive paradigm, which facilitates easier and convenient data collection using low-cost and small-size devices [36].”
BackgroundAdaptive Transmission for Edge Learning via Training Loss Estimation
Huang, X., & Zhou, S. (2020) · International Conference on Communications · doi:10.1109/icc40277.2020.9149251 · Cited by 5
“Emerging technologies like edge learning [2][3] deploy machine learning capabilities at the wireless access network to enable applications like intelligent manufacturing, environment monitoring, autonomous driving, and etc.”
BackgroundFederated Learning and Control at the Wireless Network Edge
Bennis, M. (2021) · GetMobile Mobile Computing and Communications · doi:10.1145/3447853.3447857 · Cited by 5
Self-citationEdge Computing Enabled Technologies for Secure 6G Smart Environment-An Overview
Jamil, S. U., Khan, M. A., & Rehman, S. U. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-73689-7_88 · Cited by 5
On the Convergence Rate of Federated Learning over Unreliable Networks
Feng, C., Yang, H. H., Chen, Z., Feng, D., Wang, Z., & Quek, T. Q. S. (2021) · Computing, Communications and IoT Applications (ComComAp) · doi:10.1109/comcomap53641.2021.9652996 · Cited by 5
MIMO Over-the-Air Computation for Distributed Estimation
Park, P., Shin, H., & Marco, P. D. (2023) · Applied Sciences · doi:10.3390/app13031593 · Cited by 5
Over-the-Air Federated Edge Learning with Error-Feedback One-Bit Quantization and Power Control
Liu, Y., Liu, D., Jin, R., Zhu, G., & Shi, Q. (2024) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc62609.2024.10942260 · Cited by 5
“A wealth of data generated by edge devices such as smart mobile phones has injected vitality into edge learning but has also raised concerns about data privacy [2].”
State-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
“Emergence of 5G, Ultra-Reliable-Low Latency (URLLC) networks offer promising avenues [18], however the learning frameworks themselves need to be adapted to fully utilize the benefits of these modern communication technologies.”
Deep-Learning based Multiuser Detection for NOMAPreprint
Chitti, K., Vieira, J., & Makki, B. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.11752 · Cited by 5
Learning with BOT - Bregman and Optimal Transport divergencesPreprint
Chee, A., & Loustau, S. (2021) · HAL · Cited by 5
Efficient Fully Distributed Federated Learning with Adaptive Local LinksPreprint
Georgatos, E., Mavrokefalidis, C., & Berberidis, K. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2203.12281 · Cited by 5
“, gave rise to the so-called edge ML paradigm [4].”
BackgroundTRÎNC, E.-C., Ancuți, C., Vesa, A., Simu, C., Nita, V. A., & Stolojescu-Crișan, C. (2026) · Sensors · doi:10.3390/s26072223 · Cited by 4
Active Wireless Split Learning via Online Cloud-Local Server Delta-Knowledge Distillation
Nam, H., Park, J., & Kim, S. (2023) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops57953.2023.10283579 · Cited by 4
“Especially in MEC environment, due to limited transmission power of edge devices and scarce resource of uplink channel relatively to downlink, communication from devices to cloud server in base station costs more delay than vise versa [6].”
BackgroundSelf-citationBacanli, E., & İlhan, H. (2022) · International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA) · doi:10.1109/hora55278.2022.9799881 · Cited by 4
Gradient Calibration for Non-I.I.D. Federated Learning
Li, J., Zhang, Y., Li, Y., Gong, X., & Wang, W. (2023) · doi:10.1145/3615593.3615721 · Cited by 4
“Federated learning (FL) [12] is a promising solution that enables collaborative learning across devices without sharing private data [14].”
BackgroundCell-Less Offloading of Distributed Learning Tasks in Multi-Access Edge Computing
Han, P., Liu, B., Liu, Y., & Guo, L. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3442242 · Cited by 4
Efficient Distributed Learning Over Lossy Wireless Networks
Paolini, E., Pinto, A., Valcarenghi, L., Andriolli, N., Maggiani, L., & Esposito, F. (2024) · International Conference on Network and Service Management (CNSM) · doi:10.23919/cnsm62983.2024.10814440 · Cited by 4
“…of FL algorithms within wireless network infrastructures, practical challenges, such as the unreliability of wireless channels, including symbol errors, and resource constraints, e.g., bandwidth and power, significantly hinder their efficacy [15], degrading the quality and accuracy of FL updates.”
5G-based SharkNet protocol adaptation and wireless communication links
Xie, Y., Liu, W., & Yang, Q. (2025) · Scientific Reports · doi:10.1038/s41598-025-04499-y · Cited by 4
“Licensed spectrum operation ensures robust interference immunity in industrial environments 11 .”
BayGo: Joint Bayesian Learning and Information-Aware Graph Optimization
AlShammari, T., Samarakoon, S., Elgabli, A., & Bennis, M. (2021) · International Conference on Communications · doi:10.1109/icc42927.2021.9500613 · Cited by 4
“Recently, distributed machine learning at the network edge has received significant attention thanks to its communicationefficiency, low-latency and privacy-preserving benefits [1].”
BackgroundSelf-citationImproving the Security of Wireless Network Through Cross-project Security Issue Prediction
Wu, X., Fu, W., Mu, D., Mao, D., Zhang, H., & Zheng, W. (2020) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc49849.2020.9238816 · Cited by 4
“Nowadays, wireless technology plays a critical role in our daily life [1].”
BackgroundSekine, M., & Ikada, S. (2021) · IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) · doi:10.1109/percomworkshops51409.2021.9431085 · Cited by 4
Pathak, P., Marquezan, C. C., Trivisonno, R., & Pesavento, M. (2021) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2021-fall52928.2021.9625445 · Cited by 4
A Review on 6th Generation Wireless Communication Networks Based on Artificial Intelligence
Mistry, Z., Yadav, A. K., & Kothari, M. (2021) · Lecture notes in electrical engineering · doi:10.1007/978-981-16-4149-7_24 · Cited by 4
Wang, R., & Yuan, X. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.04407 · Cited by 4
Leveraging Machine Learning for Industrial Wireless CommunicationsPreprint
Malanchini, I., Agostini, P., Alam, K., Baumgart, M., Kasparick, M., Liao, Q., Lipp, F., Marchenko, N., Michailow, N., Pries, R., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.02051 · Cited by 4
“This leads to an additional degree of complexity, e.g., due to the mobility of devices hence changing of the network topology, and at the same time interesting new optimization problems [15].”
BackgroundDAEMON Deliverable 3.1: Initial design of real-time control and VNF intelligence mechanisms
Gramaglia, M., Mhaisen, N., García‐Saavedra, A., Garcia, G., Chang, C., Vleeschauwer, D. D., Molina, M., Slamnik–Kriještorac, N., Soto, P., Camelo, M., et al. (2021) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.5745432 · Cited by 4
A Comprehensive Survey On Client Selections in Federated LearningPreprint
Gouissem, A., Chkirbene, Z., & Hamila, R. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2311.06801 · Cited by 4
“For instance, [33] proposed a framework for effective resource management for FL in the edge.”
BackgroundWireless Image Retrieval at the Edge
Jankowski, M., Gunduz, D., & Mikolajczyk, K. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2020.3036955 · Cited by 3
Learning efficiency maximization in UAV-and-RIS-aided mobile edge learning system
Liu, J., Xu, Z., Fan, R., & Wen, Z. (2024) · Computer Networks · doi:10.1016/j.comnet.2024.110756 · Cited by 3
Elgabli, A. (2025) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2025.3566464 · Cited by 3
“In response, distributed ML has gained significant attention [6], [7], [8], [9].”
UAV-Enabled Over-the-Air Federated Learning: A Hierarchical Aggregation Approach
Zhong, X., Zhong, C., Yuan, X., & Zhang, Y. A. (2025) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2025.3635287 · Cited by 3
Ak, N., Mert, M., & Duru, İ. (2025) · International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) · doi:10.1109/ismsit67332.2025.11267927 · Cited by 3
“When supported by FL and multi-agent reinforcement learning , this multilayer design delivers both privacy preservation and real-time collaboration [51].”
Reasoning-Native Agentic Communication for 6G
Seo, H., Seon, J., Kim, J. Y., Bennis, M., Choi, W., & Kim, D. I. (2026) · IEEE Network · doi:10.1109/mnet.2026.3721818 · Cited by 3
Self-citationKhan, S. A., Tashan, W., Shayea, I. A. M., Küçük, K., ÇOLAK, S. A., Chaudhry, S. A., & Yahya, K. A. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112346 · Cited by 3
AI-Driven Terahertz 6G Wireless Communication Systems: From Hardware Design to Network Intelligence
Mbakaan, C., Kpelai, J. A., & Tyavnande, M. (2025) · Journal of Librarianship and Information Science in Africa · Cited by 3
Unsupervised Feature Vector Clustering Using Temporally Coded Spiking Networks
Stratton, P. G., Hamilton, T. J., & Wabnitz, A. (2023) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn54540.2023.10191150 · Cited by 3
“applications such as internet-of-things, smart sensors, robotics, security, defence, manufacturing, transport, and aerospace [2, 12].”
BackgroundRobust Wireless Network Anomaly Detection with Collaborative Adversarial Autoencoders
Katzef, M., Cullen, A. C., Alpcan, T., & Leckie, C. A. (2023) · International Conference on Communications · doi:10.1109/icc45041.2023.10278930 · Cited by 3
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.