Filters








1,316 Hits in 3.4 sec

Low-Latency Federated Learning over Wireless Channels with Differential Privacy [article]

Kang Wei, Jun Li, Chuan Ma, Ming Ding, Cailian Chen, Shi Jin, Zhu Han, H. Vincent Poor
2021 arXiv   pre-print
In this paper, we aim to minimize FL training delay over wireless channels, constrained by overall training performance as well as each client's differential privacy (DP) requirement.  ...  In federated learning (FL), model training is distributed over clients and local models are aggregated by a central server.  ...  Differential Privacy The DP mechanism with parameters and provides a strong criterion for the privacy preservation of distributed data processing systems.  ... 
arXiv:2106.13039v2 fatcat:nxpj6wzfsvaqzjii534zbcsqgu

Federated Learning and Wireless Communications [article]

Zhijin Qin, Geoffrey Ye Li, Hao Ye
2020 arXiv   pre-print
for training a federated learning model, and federated learning for intelligent wireless applications.  ...  Federated learning becomes increasingly attractive in the areas of wireless communications and machine learning due to its powerful functions and potential applications.  ...  and low latency, which is referred to as ultra-reliable low-latency communication (URLLC).  ... 
arXiv:2005.05265v2 fatcat:psj4p3redrg43kgn53xof6d7wq

Wireless Federated Learning (WFL) for 6G Networks – Part I: Research Challenges and Future Trends [article]

Pavlos S. Bouzinis, Panagiotis D. Diamantoulakis, George K. Karagiannidis
2021 arXiv   pre-print
, termed as Wireless Federated Learning (WFL).  ...  Recently, the massive volume of generated wireless data, the privacy concerns and the increasing computing capabilities of wireless end-devices have led to the emergence of a promising decentralized solution  ...  Among the decentralized approaches, federated learning (FL) has been proposed as a promising solution for protecting the data privacy and meeting the low-latency demands [2] , [3] .  ... 
arXiv:2105.00842v1 fatcat:nbeh2ozel5h3zcztqeba7lft7q

Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications [article]

Khaled B. Letaief, Yuanming Shi, Jianmin Lu, Jianhua Lu
2021 arXiv   pre-print
In this paper, we shall provide our vision for scalable and trustworthy edge AI systems with integrated design of wireless communication strategies and decentralized machine learning models.  ...  However, state-of-the-art deep learning and big data analytics based AI systems require tremendous computation and communication resources, causing significant latency, energy consumption, network congestion  ...  grasp learned using a tactile glove [319] ) over the Tactile Internet in an ultra-reliable and low-latency manner.  ... 
arXiv:2111.12444v1 fatcat:crrbtfylvjeihogumggdnxcbpq

Federated Learning for Wireless Communications: Motivation, Opportunities and Challenges [article]

Solmaz Niknam, Harpreet S. Dhillon, Jeffery H. Reed
2020 arXiv   pre-print
Owing to its privacy-preserving nature, federated learning is particularly relevant for many wireless applications, especially in the context of fifth generation (5G) networks.  ...  for future research on federated learning in the context of wireless communications.  ...  Since local learners and the aggregator need to exchange model parameters over the wireless channel, this would give rise to the paradigm of federated learning with parameter quantization.  ... 
arXiv:1908.06847v4 fatcat:plfaupfexzd5bb3o72f3z5kskm

Securing Federated Learning: A Covert Communication-based Approach [article]

Yuan-Ai Xie, Jiawen Kang, Dusit Niyato, Nguyen Thi Thanh Van, Nguyen Cong Luong, Zhixin Liu, Han Yu
2021 arXiv   pre-print
Federated Learning Networks (FLNs) have been envisaged as a promising paradigm to collaboratively train models among mobile devices without exposing their local privacy data.  ...  Balancing privacy protection with efficient distributed model training is a key challenge for FLNs.  ...  COVERT COMMUNICATION-BASED FEDERATED LEARNING A.  ... 
arXiv:2110.02221v1 fatcat:h6arwvyi5ncdvknzbl4olrceha

Federated Learning for UAVs-Enabled Wireless Networks: Use Cases, Challenges, and Open Problems

Bouziane Brik, Adlen Ksentini, Maha Bouaziz
2020 IEEE Access  
Due to its privacy-preserving and low communication overhead and latency, FDL is much more adequate for many UAVs-enabled wireless applications.  ...  INDEX TERMS Deep learning, federated deep learning, UAVs-based wireless networks, wireless communications.  ...  It also introduces a lower latency to generate learning models and hence supports the ultra low latency requirement of the emergent UAV-based applications.  ... 
doi:10.1109/access.2020.2981430 fatcat:7jbg7xcav5bifiniyxyubq4s7y

Guest Editorial Special Issue on Distributed Learning Over Wireless Edge Networks—Part I

Mingzhe Chen, Deniz Gunduz, Kaibin Huang, Walid Saad, Mehdi Bennis, Aneta Vulgarakis Feljan, H. Vincent Poor
2021 IEEE Journal on Selected Areas in Communications  
With that said, distributed training still requires a substantial amount of information exchange between devices and edge servers over wireless links.  ...  The avoidance of raw-data uploading not only helps to preserve privacy but may also alleviate network-traffic congestion and minimize latency.  ...  In [A15] , Seif et al. consider the optimization of training federated stochastic gradient descent (FedSGD) over fading multiple access channels, subject to central and local differential privacy constraints  ... 
doi:10.1109/jsac.2021.3118484 fatcat:potsxdjmfje4njbhrb2obwgfpu

Editorial: Introduction to the Issue on Distributed Machine Learning for Wireless Communication

Ping Yang, Octavia A. Dobre, Ming Xiao, Marco Di Renzo, Jun Li, Tony Q. S. Quek, Zhu Han
2022 IEEE Journal on Selected Topics in Signal Processing  
The sixteenth paper, entitled "Loss-Privacy Tradeoff in Federated Edge Learning," proposes a personalized differential privacy based federated mobile edge learning (FMEL) scheme to alleviate the privacy  ...  with only local channel state information (CSI) as input.  ... 
doi:10.1109/jstsp.2022.3165356 fatcat:dab46w4tone55oow6gquetnp6m

Edge Learning for B5G Networks with Distributed Signal Processing: Semantic Communication, Edge Computing, and Wireless Sensing [article]

Wei Xu, Zhaohui Yang, Derrick Wing Kwan Ng, Marco Levorato, Yonina C. Eldar, M'erouane Debbah
2022 arXiv   pre-print
To process and transfer large amounts of data in emerging wireless services, it has become increasingly appealing to exploit distributed data communication and learning.  ...  Also, recent achievements of enabling techniques for the dual-functional design are surveyed with exemplifications from the mutual perspectives of "communications for learning" and "learning for communications  ...  In particular, the authors first proved that channel noise can be used to achieve differential privacy in FL.  ... 
arXiv:2206.00422v1 fatcat:osp426emrngi3bvye6fmk7kqce

Differentially Private AirComp Federated Learning with Power Adaptation Harnessing Receiver Noise [article]

Yusuke Koda, Koji Yamamoto, Takayuki Nishio, Masahiro Morikura
2020 arXiv   pre-print
Over-the-air computation (AirComp)-based federated learning (FL) enables low-latency uploads and the aggregation of machine learning models by exploiting simultaneous co-channel transmission and the resultant  ...  To understand this tradeoff more fully, the closed-form expressions of SNR (with respect to the privacy level) are derived, and the tradeoff is analytically demonstrated.  ...  Regarding the first issue of upload latency over wireless multiple-access channels, over-the-air computation (AirComp) has emerged as a promising approach [6] - [10] .  ... 
arXiv:2004.06337v1 fatcat:av3xtswor5euxewli5jfaf5cgm

Knowledge Distillation For Wireless Edge Learning [article]

Ahmed P. Mohamed, Abu Shafin Mohammad Mahdee Jameel, Aly El Gamal
2021 arXiv   pre-print
Using this close-to-practice dataset, we find that widely used federated learning approaches, specially those that are privacy preserving, are worse than local training for a wide range of settings.  ...  The proposed framework achieves overall better performance than both local and federated training approaches, while being robust against catastrophic failures as well as challenging channel conditions  ...  g t+1 : g t+1 = N i=1 w i N . (1) Differential Privacy Federated Averaging (DP-Fed): is the original FedAvg technique incorporating differential privacy as a solution to solve the privacy issue.  ... 
arXiv:2104.06374v1 fatcat:4frmsvmnwnaxvehddvhbeob4na

Reconfigurable Intelligent Surface Empowered Over-the-Air Federated Edge Learning [article]

Hang Liu, Zehong Lin, Xiaojun Yuan, Ying-Jun Angela Zhang
2022 arXiv   pre-print
Federated edge learning (FEEL) has emerged as a revolutionary paradigm to develop AI services at the edge of 6G wireless networks as it supports collaborative model training at a massive number of mobile  ...  However, model communication over wireless channels, especially in uplink model uploading of FEEL, has been widely recognized as a bottleneck that critically limits the efficiency of FEEL.  ...  With RIS, the wireless channel can be configured to achieve diverse system requirements at a low cost by optimizing the RIS phase shifts.  ... 
arXiv:2109.02353v2 fatcat:fpi7xru5tfghvbddd3z3teb4ba

From Federated to Fog Learning: Distributed Machine Learning over Heterogeneous Wireless Networks [article]

Seyyedali Hosseinalipour and Christopher G. Brinton and Vaneet Aggarwal and Huaiyu Dai and Mung Chiang
2020 arXiv   pre-print
There are several challenges with employing conventional federated learning in contemporary networks, due to the significant heterogeneity in compute and communication capabilities that exist across devices  ...  It considers a multi-layer hybrid learning framework consisting of heterogeneous devices with various proximities.  ...  These physical/link-layer technologies can be developed jointly with fog learning to conduct model training over large numbers of users with high data rates and low latency. 12) Deep reinforcement learning  ... 
arXiv:2006.03594v3 fatcat:mpcav4qexvgwdmnvvr4qzuiblm

Digital Twin of Wireless Systems: Overview, Taxonomy, Challenges, and Opportunities [article]

Latif U. Khan, Zhu Han, Walid Saad, Ekram Hossain, Mohsen Guizani, Choong Seon Hong
2022 arXiv   pre-print
learning, so as to enable the smart applications.  ...  ., user-defined quality of experience metrics, latency, and reliability) that are challenging to be fulfilled by existing wireless systems.  ...  In over-the-air computation, the channel noise is considered a differential privacy noise for preserving the distributed learning privacy.  ... 
arXiv:2202.02559v1 fatcat:v6afo5n2srfqle3se3zbjarzeq
« Previous Showing results 1 — 15 out of 1,316 results