{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,5]],"date-time":"2025-04-05T11:07:51Z","timestamp":1743851271941,"version":"3.37.3"},"reference-count":186,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1908308"],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000781","name":"European Research Council (ERC) through the Starting","doi-asserted-by":"publisher","award":["BEACON 677854"],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"U.K. Engineering and Physical Sciences Research Council (EPSRC) through the CHIST-ERA Program","doi-asserted-by":"publisher","award":["EP\/T023600\/1"],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research (ONR) under MURI","doi-asserted-by":"publisher","award":["N00014-19-1-2621"],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002341","name":"Academy of Finland 6G Flagship","doi-asserted-by":"publisher","award":["318927"],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"publisher"}]},{"name":"project SMARTER"},{"name":"projects EU-ICT IntellIoT and EUCHISTERA LearningEdge"},{"name":"CONNECT, Infotech-NOOR, and NEGEIN"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Select. Areas Commun."],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1109\/jsac.2021.3118346","type":"journal-article","created":{"date-parts":[[2021,10,6]],"date-time":"2021-10-06T22:46:54Z","timestamp":1633560414000},"page":"3579-3605","source":"Crossref","is-referenced-by-count":370,"title":["Distributed Learning in Wireless Networks: Recent Progress and Future Challenges"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2570-703X","authenticated-orcid":false,"given":"Mingzhe","family":"Chen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7725-395X","authenticated-orcid":false,"given":"Deniz","family":"Gunduz","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8773-4629","authenticated-orcid":false,"given":"Kaibin","family":"Huang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2247-2458","authenticated-orcid":false,"given":"Walid","family":"Saad","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0261-0171","authenticated-orcid":false,"given":"Mehdi","family":"Bennis","sequence":"additional","affiliation":[]},{"given":"Aneta Vulgarakis","family":"Feljan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2062-131X","authenticated-orcid":false,"given":"H. Vincent","family":"Poor","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2018.2850303"},{"journal-title":"Pytorch Implementations of the Multi-Agent Reinforcement Learning Algorithms","year":"2021","key":"ref172"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3088689"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3063822"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2013.060513.120959"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3041401"},{"key":"ref178","article-title":"Cooperative multi-agent reinforcement learning for low-level wireless communication","author":"de vrieze","year":"2018","journal-title":"arXiv 1801 04541"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9014325"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2020.2966989"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2871070"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2000410"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2784180"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2000382"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2986024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2008.929967"},{"key":"ref36","first-page":"3557","article-title":"Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach","volume":"33","author":"fallah","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","article-title":"Federated multi-task learning","author":"smith","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2017","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2021.3078100"},{"key":"ref180","article-title":"Correlation-aware cooperative multigroup broadcast 360° video delivery network: A hierarchical deep reinforcement learning approach","author":"hu","year":"2020","journal-title":"arXiv 2010 11347"},{"key":"ref185","article-title":"Learning to schedule communication in multi-agent reinforcement learning","author":"kim","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref184","article-title":"Communication efficient parallel reinforcement learning","author":"agarwal","year":"2021","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref183","article-title":"Deployment-efficient reinforcement learning via model-based offline optimization","author":"matsushima","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/CDC40024.2019.9029257"},{"key":"ref186","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"Proc Conf Mach Learn"},{"key":"ref28","first-page":"5976","article-title":"The convergence of sparsified gradient methods","author":"alistarh","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1045"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3021017"},{"key":"ref29","first-page":"4448","article-title":"Sparsified SGD with memory","author":"stich","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900103"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.2000045"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-274"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3055679"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC51858.2021.9593155"},{"key":"ref26","first-page":"1","article-title":"TernGrad: Ternary gradients to reduce communication in distributed deep learning","author":"wen","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"journal-title":"Fundamentals of LTE","year":"2010","author":"arunabha","key":"ref100"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-354"},{"key":"ref50","article-title":"Expanding the reach of federated learning by reducing client resource requirements","author":"caldas","year":"2018","journal-title":"arXiv 1812 07210"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041185"},{"key":"ref154","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","author":"han","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref153","article-title":"Compressing deep convolutional networks using vector quantization","author":"gong","year":"2014","journal-title":"arXiv 1412 6115"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037698"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.226"},{"key":"ref150","article-title":"Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or ?1","author":"courbariaux","year":"2016","journal-title":"arXiv 1602 02830 [cs]"},{"key":"ref152","article-title":"Compressing neural networks with the hashing trick","author":"chen","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref151","article-title":"Neural networks with few multiplications","author":"lin","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref146","article-title":"Learning structured sparsity in deep neural networks","author":"wen","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref147","article-title":"Deep learning with limited numerical precision","author":"gupta","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref148","article-title":"Training deep neural networks with low precision multiplications","author":"courbariaux","year":"2015","journal-title":"Proc Int Conf Learn Represent Workshop"},{"key":"ref149","article-title":"BinaryConnect: Training deep neural networks with binary weights during propagations","author":"courbariaux","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref59","article-title":"FedPAQ: A communication-efficient federated learning method with periodic averaging and quantization","author":"reisizadeh","year":"2020","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref58","article-title":"Natural compression for distributed deep learning","author":"horvath","year":"2019","journal-title":"arXiv 1905 10988"},{"key":"ref57","first-page":"1709","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","author":"alistarh","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref56","article-title":"FetchSGD: Communication-efficient federated learning with sketching","author":"rothchild","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC48557.2020.9154309"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3041388"},{"key":"ref53","article-title":"Hyper-sphere quantization: Communication-efficient SGD for federated learning","author":"dai","year":"2019","journal-title":"arXiv 1911 04655"},{"key":"ref52","article-title":"Optimal gradient compression for distributed and federated learning","author":"albasyoni","year":"2020","journal-title":"arXiv 2010 03246"},{"key":"ref40","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representation"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2987203"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1063\/1.52104"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/5.790634"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139030687"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2000373"},{"key":"ref162","article-title":"Improving device-edge cooperative inference of deep learning via 2-step pruning","author":"shi","year":"2019","journal-title":"Proc IEEE Conf Comput Commun Workshops"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/ISLPED.2019.8824955"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/PADSW.2018.8645013"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.2000430"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41928-019-0355-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900461"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2019.1800286"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900370"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2018.8639121"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/JCC.2020.09.009"},{"key":"ref49","first-page":"2350","article-title":"Federated learning with compression: Unified analysis and sharp guarantees","volume":"130","author":"haddadpour","year":"2021","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2947893"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900119"},{"journal-title":"Portable Network Graphics (PNG)","year":"2019","key":"ref158"},{"key":"ref46","article-title":"signSGD with majority vote is communication efficient and fault tolerant","author":"bernstein","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref45","article-title":"SignSGD: Compressed optimisation for non-convex problems","author":"bernstein","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2024789118"},{"key":"ref47","article-title":"Error feedback fixes SignSGD and other gradient compression schemes","author":"karimireddy","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref42","article-title":"Gradient sparsification for communication-efficient distributed optimization","author":"wangni","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref41","article-title":"Sparse communication for training deep networks","author":"eghlidi","year":"2020","journal-title":"arXiv 2009 09271"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298623"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT45174.2021.9518221"},{"key":"ref127","article-title":"Ensemble distillation for robust model fusion in federated learning","author":"lin","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref126","article-title":"FedMD: Heterogenous federated learning via model distillation","author":"li","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst Workshop Federated Learn Data Privacy Confidentiality"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC.2019.8904164"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053448"},{"key":"ref73","article-title":"Federated generalized Bayesian learning via distributed stein variational gradient descent","author":"kassab","year":"2020","journal-title":"arXiv 2009 06419"},{"key":"ref72","first-page":"1","article-title":"Communication-efficient distributed learning via lazily aggregated quantized gradients","author":"sun","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref71","article-title":"LAG: Lazily aggregated gradient for communication-efficient distributed learning","author":"chen","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2020.3003693"},{"key":"ref70","article-title":"Multi-stage hybrid federated learning over large-scale D2D-enabled fog networks","author":"hosseinalipour","year":"2020","journal-title":"arXiv 2007 09511"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/216"},{"key":"ref76","first-page":"21394","article-title":"Personalized federated learning with Moreau envelopes","author":"dinh","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref77","article-title":"An efficient framework for clustered federated learning","author":"ghosh","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref130","article-title":"Federated knowledge distillation","author":"seo","year":"2020","journal-title":"arXiv 2011 02367"},{"key":"ref74","article-title":"Don’t use large mini-batches, use local SGD","author":"lin","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015693"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3036955"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC48557.2020.9154306"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118400"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/13\/07\/P07027"},{"key":"ref79","article-title":"Fair resource allocation in federated learning","author":"li","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref132","article-title":"Fast deep learning for automatic modulation classification","author":"ramjee","year":"2019","journal-title":"arXiv 1901 05850"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1962.1057738"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWorkshops49005.2020.9145068"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2019.2953750"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1970.1054469"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3103874"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2019.8849432"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737464"},{"key":"ref61","article-title":"Federated optimization: Distributed machine learning for on-device intelligence","author":"kone?n\u00fd","year":"2016","journal-title":"arXiv 1610 02527"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904348"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/SPAWC48557.2020.9154285"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2944169"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2003.818410"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.3035770"},{"key":"ref141","article-title":"Comparing biases for minimal network construction with back-propagation","author":"hanson","year":"1989","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3025446"},{"key":"ref142","article-title":"Optimal brain damage","author":"lecun","year":"1990","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3008091"},{"key":"ref143","article-title":"Optimal Brain Surgeon: Extensions and performance comparison","author":"hassibi","year":"1993","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3031503"},{"key":"ref144","article-title":"Pruning algorithms to accelerate convolutional neural networks for edge applications: A survey","author":"liu","year":"2020","journal-title":"arXiv 2005 04275"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3010896"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.280"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1900271"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2005.861896"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118348"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2173632"},{"key":"ref108","article-title":"1-bit compressive sensing for efficient federated learning over the air","author":"fan","year":"2021","journal-title":"arXiv 2103 16055"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2007.904785"},{"key":"ref107","article-title":"Joint optimization of communications and federated learning over the air","author":"fan","year":"2021","journal-title":"arXiv 2104 03490"},{"key":"ref92","article-title":"Efficient decentralized deep learning by dynamic model averaging","author":"kamp","year":"2018","journal-title":"arXiv 1807 03210"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3039309"},{"key":"ref91","article-title":"Gradient coding: Avoiding stragglers in distributed learning","author":"xu","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3065748"},{"key":"ref90","article-title":"Revisiting distributed synchronous SGD","author":"chen","year":"2016","journal-title":"arXiv 1604 00981"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3012287"},{"key":"ref103","article-title":"Optimized power control for over-the-air federated edge learning","author":"cao","year":"2020","journal-title":"arXiv 2011 05587"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2009.0901.070075"},{"key":"ref111","article-title":"Edge federated learning via unit-modulus over-the-air computation (extended version)","author":"wang","year":"2021","journal-title":"arXiv 2101 12051"},{"key":"ref112","article-title":"Collaborative machine learning at the wireless edge with blind transmitters","author":"amiri","year":"2021","journal-title":"IEEE Trans Wireless Commun"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2961673"},{"key":"ref98","article-title":"Over-the-air computing for wireless data aggregation in massive IoT","author":"zhu","year":"2020","journal-title":"arXiv 2009 02181"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247X(79)90091-X"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2013.072913.120815"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2843321"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3058573"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3024629"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054634"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2981904"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2946245"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.2974748"},{"key":"ref82","article-title":"Deep leakage from gradients","author":"zhu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","article-title":"Towards federated learning at scale: System design","author":"bonawitz","year":"2019","journal-title":"Proc Syst Mach Learn Conf"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2020.3036948"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2000397"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322199"},{"key":"ref84","article-title":"Multi-institutional deep learning modeling without sharing patient data: A feasibility study on brain tumor segmentation","author":"sheller","year":"2018","journal-title":"Proc Int MICCAI Brainlesion Workshop"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.2000478"},{"key":"ref83","article-title":"Federated learning: Collaborative machine learning without centralized training data","volume":"3","author":"mcmahan","year":"2017","journal-title":"Google Research Blog"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2000744"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT45174.2021.9518031"},{"key":"ref114","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1561\/0400000042","article-title":"The algorithmic foundations of differential privacy","volume":"9","author":"dwork","year":"2014","journal-title":"Found Trends Theor Comput Sci"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00029"},{"key":"ref80","article-title":"Heterogeneity for the win: One-shot federated clustering","author":"dennis","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT44484.2020.9174426"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322479"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413624"},{"key":"ref121","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref122","article-title":"Communication-efficient on-device machine learning: Federated distillation and augmentation under non-IID private data","author":"jeong","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst Workshop Mach Learn Phone Consum Devices"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2020.2994942"},{"journal-title":"AI FL for IoT","year":"0","author":"rojek","key":"ref85"},{"article-title":"FL for time series forecasting using LSTM networks: Exploiting similarities through clustering","year":"2019","author":"gonz\u00e1lez","key":"ref86"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3349611.3355548"},{"journal-title":"Privacy-aware machine learning with low network footprint","year":"2019","author":"vandikas","key":"ref88"}],"container-title":["IEEE Journal on Selected Areas in Communications"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/49\/9620733\/9562559-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/49\/9620733\/09562559.pdf?arnumber=9562559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:48:07Z","timestamp":1649443687000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9562559\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":186,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/jsac.2021.3118346","relation":{},"ISSN":["0733-8716","1558-0008"],"issn-type":[{"type":"print","value":"0733-8716"},{"type":"electronic","value":"1558-0008"}],"subject":[],"published":{"date-parts":[[2021,12]]}}}