{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T22:57:29Z","timestamp":1785020249208,"version":"3.55.0"},"reference-count":205,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation (NRF), Singapore, through Singapore Energy Market Authority, Energy Resilience","doi-asserted-by":"publisher","award":["NRF2017EWT-EP003-041"],"award-info":[{"award-number":["NRF2017EWT-EP003-041"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation (NRF), Singapore, through Singapore Energy Market Authority, Energy Resilience","doi-asserted-by":"publisher","award":["NRF2015-NRF-ISF001-2277"],"award-info":[{"award-number":["NRF2015-NRF-ISF001-2277"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001381","name":"Singapore NRF National Satellite of Excellence, Design Science and Technology for Secure Critical Infrastructure","doi-asserted-by":"publisher","award":["NSoE DeST-SCI2019-0007"],"award-info":[{"award-number":["NSoE DeST-SCI2019-0007"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"A*STAR-NTU-SUTD Joint Research Grant Call on Artificial Intelligence for the Future of Manufacturing","award":["RGANS1906"],"award-info":[{"award-number":["RGANS1906"]}]},{"name":"A*STAR-NTU-SUTD Joint Research Grant Call on Artificial Intelligence for the Future of Manufacturing","award":["WASP\/NTUM4082187(4080)"],"award-info":[{"award-number":["WASP\/NTUM4082187(4080)"]}]},{"name":"Singapore MOE Tier 2","award":["MOE2014-T2-2-015 ARC4\/15"],"award-info":[{"award-number":["MOE2014-T2-2-015 ARC4\/15"]}]},{"name":"Singapore MOE Tier 2","award":["MOE Tier 1 2017-T1-002-007 RG122\/17"],"award-info":[{"award-number":["MOE Tier 1 2017-T1-002-007 RG122\/17"]}]},{"name":"AI Singapore Programme","award":["AISG-GC-2019-003"],"award-info":[{"award-number":["AISG-GC-2019-003"]}]},{"name":"AI Singapore Programme","award":["NRF-NRFI05-2019-0002"],"award-info":[{"award-number":["NRF-NRFI05-2019-0002"]}]},{"name":"Alibaba-NTU Singapore Joint Research Institute","award":["Alibaba-NTU-AIR2019B1"],"award-info":[{"award-number":["Alibaba-NTU-AIR2019B1"]}]},{"DOI":"10.13039\/501100001475","name":"Nanyang Technological University, Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001475","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012046","name":"Vietnam National Foundation for Science and Technology Development","doi-asserted-by":"publisher","award":["102.02-2019.305"],"award-info":[{"award-number":["102.02-2019.305"]}],"id":[{"id":"10.13039\/100012046","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61631005"],"award-info":[{"award-number":["61631005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1801261"],"award-info":[{"award-number":["U1801261"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Basic Research Program of China","doi-asserted-by":"publisher","award":["2018YFB1801105"],"award-info":[{"award-number":["2018YFB1801105"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013314","name":"Higher Education Discipline Innovation Project","doi-asserted-by":"publisher","award":["B20064"],"award-info":[{"award-number":["B20064"]}],"id":[{"id":"10.13039\/501100013314","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hong Kong CERG","award":["16209715"],"award-info":[{"award-number":["16209715"]}]},{"name":"Hong Kong CERG","award":["16244616"],"award-info":[{"award-number":["16244616"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Commun. Surv. Tutorials"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/comst.2020.2986024","type":"journal-article","created":{"date-parts":[[2020,4,8]],"date-time":"2020-04-08T21:17:30Z","timestamp":1586380650000},"page":"2031-2063","source":"Crossref","is-referenced-by-count":2193,"title":["Federated Learning in Mobile Edge Networks: A Comprehensive Survey"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2150-5561","authenticated-orcid":false,"given":"Wei Yang Bryan","family":"Lim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4299-3456","authenticated-orcid":false,"given":"Nguyen Cong","family":"Luong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9528-0863","authenticated-orcid":false,"given":"Dinh Thai","family":"Hoang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8794-6330","authenticated-orcid":false,"given":"Yutao","family":"Jiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2671-5090","authenticated-orcid":false,"given":"Ying-Chang","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5059-8360","authenticated-orcid":false,"given":"Qiang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7442-7416","authenticated-orcid":false,"given":"Dusit","family":"Niyato","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0300-3448","authenticated-orcid":false,"given":"Chunyan","family":"Miao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.3485"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1700332"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/WF-IoT.2014.6803166"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.3390\/app8122663"},{"key":"ref173","author":"nguyen","year":"2018","journal-title":"D_IoT A crowdsourced self-learning approach for detecting compromised IoT devices"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2018.8647616"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2919736"},{"key":"ref178","author":"chen","year":"2018","journal-title":"Federated echo state learning for minimizing breaks in presence in wireless virtual reality networks"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.07.069"},{"key":"ref168","author":"kim","year":"2018","journal-title":"On-device federated learning via blockchain and its latency analysis"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2019.2952332"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11036-012-0368-0"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-018-0834-5"},{"key":"ref33","author":"samarakoon","year":"2018","journal-title":"Distributed federated learning for ultra-reliable low-latency vehicular communications"},{"key":"ref32","author":"wang","year":"2018","journal-title":"In-edge AI Intelligentizing mobile edge computing caching and communication by federated learning"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCW.2018.8403664"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2918951"},{"key":"ref36","author":"li","year":"2019","journal-title":"Federated learning Challenges methods and future directions"},{"key":"ref35","author":"niknam","year":"2019","journal-title":"Federated Learning for Wireless Communications Motivation Opportunities and Challenges"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2018.8376973"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9013587"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-76464-1"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/MilCIS.2015.7348942"},{"key":"ref182","year":"2019","journal-title":"NSL-KDD"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14660-2_3"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2017.2680898"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.4218\/etrij.10.1510.0054"},{"key":"ref186","first-page":"2249","article-title":"An empirical evaluation of Thompson sampling","author":"chapelle","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2881442"},{"key":"ref27","author":"verma","year":"2018","journal-title":"Federated AI for building AI solutions across multiple agencies"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/GLOCOM.2018.8647927"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2904897"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2775739"},{"key":"ref21","author":"mcmahan","year":"2016","journal-title":"Feder-ated learning of deep networks using model averaging"},{"key":"ref24","author":"hard","year":"2018","journal-title":"Federated learning for mobile keyboard prediction"},{"key":"ref23","author":"mcmahan","year":"2016","journal-title":"Communication-efficient learning of deep networks from decentralized data"},{"key":"ref26","author":"powell","year":"2019","journal-title":"Nvidia Clara Federated Learning to Deliver AI to Hospitals While Protecting Patient Data"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2018.01.007"},{"key":"ref50","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/BF00332918"},{"key":"ref154","author":"geyer","year":"2017","journal-title":"Differentially private federated learning A client level perspective"},{"key":"ref153","first-page":"265","article-title":"Calibrating noise to sensitivity in private data analysis","author":"dwork","year":"2006","journal-title":"Proc Theory Cryptography Conf"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref155","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1145\/2810103.2813687","article-title":"Privacy-preserving deep learning","author":"shokri","year":"2015","journal-title":"Proc ACM SIGSAC Conf Comput Commun Security"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"ref152","first-page":"197","article-title":"Practical evasion of a learning-based classifier: A case study","author":"laskov","year":"2014","journal-title":"Proc IEEE Symp Security Privacy"},{"key":"ref151","author":"papernot","year":"2016","journal-title":"Transferability in machine learning from phenomena to black-box attacks using adversarial samples"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2014.7025068"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1504\/IJSN.2015.071829"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1145\/2810103.2813677"},{"key":"ref149","first-page":"601","article-title":"Stealing machine learning models via prediction APIS","author":"tram\u00e8r","year":"2016","journal-title":"Proc Symp SecurityPrivacy"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.02.010"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-017-1053-3"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2749125"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.10.006"},{"key":"ref53","first-page":"1045","article-title":"Recurrent neural network based language model","author":"mikolov","year":"2010","journal-title":"Proc 11th Annu Conf Int Speech Commun Assoc"},{"key":"ref52","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Proc Adv Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2750180"},{"key":"ref167","author":"bagdasaryan","year":"2018","journal-title":"How to backdoor federated learning"},{"key":"ref166","author":"bhagoji","year":"2018","journal-title":"Analyzing federated learning through an adversarial lens"},{"key":"ref165","author":"dua","year":"2019","journal-title":"UCI Machine Learning Repository"},{"key":"ref164","author":"fung","year":"2018","journal-title":"Mitigating sybils in federated learning poisoning"},{"key":"ref163","author":"chen","year":"2017","journal-title":"Targeted backdoor attacks on deep learning systems using data poisoning"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761267"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2017.2787987"},{"key":"ref160","author":"triastcyn","year":"2019","journal-title":"Federated generative privacy"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2011.6069707"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2762003"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SAS.2015.7133628"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2014.2299233"},{"key":"ref159","author":"liu","year":"2019","journal-title":"Boosting Privately Privacy-Preserving Federated Extreme Boosting for Mobile Crowdsensing"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2519502"},{"key":"ref49","author":"radford","year":"2015","journal-title":"Unsupervised Representation learning with deep convolutional generative adversarial networks CoRR"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3134012"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2017.02.006"},{"key":"ref158","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2014.2325029"},{"key":"ref48","article-title":"Semi-supervised learning literature survey","author":"zhu","year":"2005"},{"key":"ref47","first-page":"249","article-title":"Neural networks for machine learning lecture 6A overview of mini-batch gradient descent","volume":"14","author":"hinton","year":"2012","journal-title":"Cited"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2908280"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2685434"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref43","first-page":"184","article-title":"Learning a deep convolutional network for image super-resolution","author":"dong","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref73","author":"arivazhagan","year":"2019","journal-title":"Federated learning with personalization layers"},{"key":"ref72","first-page":"351","article-title":"Convergence of alternating optimization","volume":"11","author":"bezdek","year":"2003","journal-title":"Neural Parallel Sci Comput"},{"key":"ref71","first-page":"3068","article-title":"Communication-efficient distributed dual coordinate ascent","author":"jaggi","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04898-2_327"},{"key":"ref76","author":"huang","year":"2018","journal-title":"Loadaboost Loss-based adaboost federated machine learning on medical data"},{"key":"ref77","author":"bonawitz","year":"2019","journal-title":"Towards Federated Learning at Scale System Design"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.76"},{"key":"ref75","author":"li","year":"2019","journal-title":"On the convergence of FEDAVG on non-IID data"},{"key":"ref78","author":"nishio","year":"2018","journal-title":"Client selection for federated learning with heterogeneous resources in mobile edge"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133982"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2940820"},{"key":"ref62","volume":"2","author":"myers","year":"1990","journal-title":"Classical and Modern Regression with Applications"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009715923555"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904348"},{"key":"ref64","author":"lin","year":"2018","journal-title":"Don 't use large mini-batches use local sgd"},{"key":"ref65","author":"zhao","year":"2018","journal-title":"Federated learning with non-IID data"},{"key":"ref66","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1023\/A:1026543900054"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD46524.2019.00038"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA.2016.7797091"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2019.00044"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC48107.2020.9148475"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/ICSMC.2000.886455"},{"key":"ref193","volume":"20","author":"bradley","year":"2000","journal-title":"Constrained K-Means Clustering"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2828144"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1186\/s13174-018-0087-2"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1145\/3302505.3310070"},{"key":"ref95","first-page":"1","article-title":"ESGD: Communication efficient distributed deep learning on the edge","author":"tao","year":"2018","journal-title":"Proceedings of USENIX Workshop on Hot Topics in Edge Computing (HotEdge 18)"},{"key":"ref94","author":"caldas","year":"2018","journal-title":"Expanding the reach of federated learning by reducing client resource requirements"},{"key":"ref190","author":"de haan","year":"2007","journal-title":"Extreme Value Theory An Introduction"},{"key":"ref93","first-page":"4447","article-title":"Sparsified SGD with memory","author":"stich","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.2200\/S00271ED1V01Y201006CNT007"},{"key":"ref92","first-page":"9850","article-title":"ATOMO: Communication-efficient learning via atomic sparsification","author":"wang","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/SmartGridComm.2014.7007732"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2019.00099"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref98","author":"liu","year":"2019","journal-title":"A communication efficient vertical federated learning framework"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2018.8698609"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref97","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref82","year":"2019","journal-title":"TensorFlow federated Machine learning on decentralized data"},{"key":"ref81","first-page":"1","article-title":"Learning differentially private recurrent language models","author":"mcmahan","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref84","author":"caldas","year":"2018","journal-title":"LEAF A benchmark for federated settings"},{"key":"ref83","author":"ryffel","year":"2018","journal-title":"A generic framework for privacy preserving deep learning"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15328-0_17"},{"key":"ref89","author":"kone?n?","year":"2016","journal-title":"Federated learning Strategies for improving communication efficiency"},{"key":"ref85","author":"lecun","year":"2010","journal-title":"MNIST Handwritten Digit Database"},{"key":"ref86","author":"go","year":"2016","journal-title":"Sentiment140 Site Functionality 2013c"},{"key":"ref87","year":"2018","journal-title":"Fate An Industrial Grade Federated Learning Framework"},{"key":"ref88","author":"kone?n?","year":"2016","journal-title":"Federated optimization distributed machine learning for on-device intelligence"},{"key":"ref200","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1109\/MNET.2006.1637931","article-title":"Jamming sensor networks: Attack and defense strategies","volume":"20","author":"xu","year":"2006","journal-title":"IEEE Netw"},{"key":"ref101","first-page":"97","article-title":"Learning transferable features with deep adaptation networks","author":"long","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref100","author":"liu","year":"2019","journal-title":"Edge-assisted hierarchical federated learning with non-iid data"},{"key":"ref203","author":"singh","year":"2019","journal-title":"Detailed comparison of communication efficiency of split learning and federated learning"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2009.08.006"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2008.9"},{"key":"ref202","author":"vepakomma","year":"2018","journal-title":"Split learning for health Distributed deep learning without sharing raw patient data"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2014.2379715"},{"key":"ref127","author":"zhu","year":"2018","journal-title":"Low-latency broadband analog aggregation for federated edge learning"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2009.5277454"},{"key":"ref125","author":"chen","year":"2020","journal-title":"Convergence time optimization for federated learning over wireless networks"},{"key":"ref124","author":"li","year":"2019","journal-title":"Fair resource allocation in federated learning"},{"key":"ref129","author":"amiri","year":"2019","journal-title":"Federated learning over wireless fading channels"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2011.2165816"},{"key":"ref130","author":"yang","year":"2018","journal-title":"Federated learning via over-the-air computation"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1137\/050642691"},{"key":"ref134","author":"xie","year":"2019","journal-title":"Asynchronous federated optimization"},{"key":"ref131","author":"keskar","year":"2016","journal-title":"On large-batch training for deep learning Generalization gap and sharp minima"},{"key":"ref132","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/s10479-004-5022-1","article-title":"The DC (difference of convex functions) programming and DCA revisited with DC models of real world nonconvex optimization problems","volume":"133","author":"tao","year":"2005","journal-title":"Ann Oper Res"},{"key":"ref136","volume":"3","author":"osborne","year":"2004","journal-title":"An Introduction to Game Theory"},{"key":"ref135","author":"feng","year":"2018","journal-title":"Joint service pricing and cooperative relay communication for federated learning"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2967772"},{"key":"ref137","author":"sarikaya","year":"2019","journal-title":"Motivating workers in federated learning A Stackelberg game perspective"},{"key":"ref139","author":"khan","year":"2019","journal-title":"Federated learning for edge networks Resource optimization and incentive mechanism"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/VTS-APWCS.2019.8851649"},{"key":"ref141","author":"bolton","year":"2005","journal-title":"Contract Theory"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2968399"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/ICITST.2015.7412073"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CBMS.2015.26"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1145\/3375627.3375840"},{"key":"ref1","author":"lueth","year":"2019","journal-title":"State of the IoT 2018 Number of IoT devices now at 7B market accelerating"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00029"},{"key":"ref109","author":"lin","year":"2017","journal-title":"Deep Gradient Compression Reducing the Communication Bandwidth for Distributed Training"},{"key":"ref108","author":"chen","year":"2016","journal-title":"Revisiting Distributed Synchronous SGD"},{"key":"ref107","first-page":"1488","article-title":"Scalable distributed DNN training using commodity GPU cloud computing","author":"strom","year":"2015","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref106","author":"cohen","year":"2017","journal-title":"EMNIST an extension of MNIST to handwritten letters"},{"key":"ref105","first-page":"334","article-title":"Diameters of some finite-dimensional sets and classes of smooth functions","volume":"41","author":"kashin","year":"1977","journal-title":"Izvestiya Rossiiskoi Akademii Nauk Seriya Matematicheskaya"},{"key":"ref104","first-page":"3329","article-title":"Distributed mean estimation with limited communication","author":"suresh","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref103","author":"han","year":"2015","journal-title":"Deep compression Compressing deep neural networks with pruning trained quantization and huffman coding"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.274"},{"key":"ref111","first-page":"1","article-title":"A public domain dataset for human activity recognition using smartphones","author":"anguita","year":"2013","journal-title":"Proc ESANN"},{"key":"ref112","author":"buscema","year":"2009","journal-title":"Semeion handwritten digit data set"},{"key":"ref110","first-page":"629","article-title":"GAIA: Geo-distributed machine learning approaching LAN speeds","author":"hsieh","year":"2017","journal-title":"Proc Symp Netw Syst Design Implement"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-6265-282-8"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2014.161"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2745201"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2017.3641638"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2018.1700202"},{"key":"ref15","author":"han","year":"2019","journal-title":"Convergence of edge computing and deep learning A comprehensive survey"},{"key":"ref16","year":"2016","journal-title":"Cisco Global Cloud Index Forecast and Methodology 2016–2021 White Paper"},{"key":"ref118","author":"yoshida","year":"2019","journal-title":"Hybrid-FL Cooperative learning mechanism using non-iid data in wireless networks"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2016.2579198"},{"key":"ref117","author":"mohri","year":"2019","journal-title":"Agnostic federated learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2015.2487344"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2682318"},{"key":"ref119","author":"anh","year":"2018","journal-title":"Efficient training management for mobile crowd-machine learning A deep reinforcement learning approach"},{"key":"ref114","first-page":"21","article-title":"Asynchronous federated learning for geospatial applications","author":"sprague","year":"2018","journal-title":"Proc Eur Conf Mach Learn Knowl Discovery Databases"},{"key":"ref113","author":"yang","year":"2019","journal-title":"Energy efficient federated learning over wireless communication networks"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6377(03)00062-2"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2018.1429274"},{"key":"ref120","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc 13th AAAI Conf Artif Intell"},{"key":"ref121","author":"nguyen","year":"2019","journal-title":"Resource allocation in mobility-aware federated learning networks A deep reinforcement learning approach"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2007.900405"},{"key":"ref123","author":"corbett-davies","year":"2018","journal-title":"The measure and mismeasure of fairness A critical review of fair machine learning"}],"container-title":["IEEE Communications Surveys & Tutorials"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9739\/9173582\/09060868.pdf?arnumber=9060868","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T16:58:58Z","timestamp":1651078738000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9060868\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":205,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/comst.2020.2986024","relation":{},"ISSN":["1553-877X","2373-745X"],"issn-type":[{"value":"1553-877X","type":"electronic"},{"value":"2373-745X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}