{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T07:01:06Z","timestamp":1781593266713,"version":"3.54.5"},"reference-count":361,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CPS1931950"],"award-info":[{"award-number":["CPS1931950"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3127448","type":"journal-article","created":{"date-parts":[[2021,11,10]],"date-time":"2021-11-10T22:08:03Z","timestamp":1636582083000},"page":"156071-156113","source":"Crossref","is-referenced-by-count":57,"title":["The Internet of Federated Things (IoFT)"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4546-324X","authenticated-orcid":false,"given":"Raed","family":"Kontar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naichen","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9929-8895","authenticated-orcid":false,"given":"Xubo","family":"Yue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5176-4180","authenticated-orcid":false,"given":"Seokhyun","family":"Chung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2506-1606","authenticated-orcid":false,"given":"Eunshin","family":"Byon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0884-6740","authenticated-orcid":false,"given":"Mosharaf","family":"Chowdhury","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7786-8110","authenticated-orcid":false,"given":"Jionghua","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wissam","family":"Kontar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6526-3317","authenticated-orcid":false,"given":"Neda","family":"Masoud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8089-7011","authenticated-orcid":false,"given":"Maher","family":"Nouiehed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6910-8827","authenticated-orcid":false,"given":"Chinedum E.","family":"Okwudire","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Garvesh","family":"Raskutti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8086-9328","authenticated-orcid":false,"given":"Romesh","family":"Saigal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karandeep","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5731-3911","authenticated-orcid":false,"given":"Zhi-Sheng","family":"Ye","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref275","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2019.2956472"},{"key":"ref274","doi-asserted-by":"publisher","DOI":"10.3390\/app10114004"},{"key":"ref277","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-937X.2008.00486.x"},{"key":"ref276","year":"2021","journal-title":"Samsung Galaxy Watch Active"},{"key":"ref361","first-page":"20865","article-title":"Gradient-EM Bayesian meta-learning","author":"zou","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref271","doi-asserted-by":"publisher","DOI":"10.1109\/HICSS.2014.304"},{"key":"ref360","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2015.2497283"},{"key":"ref270","article-title":"Meta-learning with latent embedding optimization","author":"rusu","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref170","first-page":"429","article-title":"Federated optimization in heterogeneous networks","author":"li","year":"2018","journal-title":"Proc 3rd MLSys Conf"},{"key":"ref273","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017","journal-title":"arXiv 1703 03864"},{"key":"ref272","first-page":"3","article-title":"Primer on monotone operator methods","volume":"16","author":"ryu","year":"2016","journal-title":"Comput Math Appl"},{"key":"ref172","article-title":"Fair resource allocation in federated learning","author":"li","year":"2019","journal-title":"arXiv 1905 10497"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/IEEECONF44664.2019.9049023"},{"key":"ref174","article-title":"Ditto: Fair and robust federated learning through personalization","author":"li","year":"2020","journal-title":"arXiv 2012 04221"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.2975749"},{"key":"ref176","article-title":"Meta-SGD: Learning to learn quickly for few-shot learning","author":"li","year":"2017","journal-title":"arXiv 1707 09835"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32692-0_16"},{"key":"ref178","article-title":"Think locally, act globally: Federated learning with local and global representations","author":"pu liang","year":"2020","journal-title":"arXiv 2001 01523"},{"key":"ref177","article-title":"Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent","author":"lian","year":"2017","journal-title":"arXiv 1705 09056"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313433"},{"key":"ref169","article-title":"On negative transfer and structure of latent functions in multi-output Gaussian processes","author":"li","year":"2020","journal-title":"arXiv 2004 02382"},{"key":"ref39","article-title":"Federated meta-learning with fast convergence and efficient communication","author":"chen","year":"2018","journal-title":"arXiv 1802 07876"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocy017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2015.2440093"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-20192-9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1115\/1.4030009"},{"key":"ref359","first-page":"733","article-title":"Parallelized stochastic gradient descent","volume":"23","author":"zinkevich","year":"2010","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1561\/2200000024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11837-019-03549-x"},{"key":"ref357","article-title":"Deep leakage from gradients","author":"zhu","year":"2019","journal-title":"Proc 33rd Conf Neural Inf Process Syst"},{"key":"ref267","first-page":"8388","article-title":"Robust and communication-efficient collaborative learning","author":"reisizadeh","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref358","doi-asserted-by":"publisher","DOI":"10.1097\/01.CCM.0000215112.84523.F0"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1007\/s10898-012-9951-y"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2019.1911462"},{"key":"ref355","article-title":"Federated learning with non-IID data","author":"zhao","year":"2018","journal-title":"arXiv 1806 00582"},{"key":"ref269","year":"2021","journal-title":"The Connected Enterprise"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/140954362"},{"key":"ref356","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2016.06.052"},{"key":"ref352","article-title":"FedPD: A federated learning framework with optimal rates and adaptivity to non-IID data","author":"zhang","year":"2020","journal-title":"arXiv 2005 11418"},{"key":"ref288","first-page":"1","article-title":"Federated multi-task learning","author":"smith","year":"2017","journal-title":"Proc 31st Conf Neural Inf Process Syst"},{"key":"ref351","author":"zhang","year":"2021","journal-title":"On the Connection Between FEDDYN and FEDPD"},{"key":"ref287","doi-asserted-by":"publisher","DOI":"10.1513\/AnnalsATS.202006-698OC"},{"key":"ref354","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/6430950"},{"key":"ref286","article-title":"Detailed comparison of communication efficiency of split learning and federated learning","author":"singh","year":"2019","journal-title":"arXiv 1909 09145"},{"key":"ref353","article-title":"A convex formulation for learning task relationships in multi-task learning","author":"zhang","year":"2012","journal-title":"arXiv 1203 3536"},{"key":"ref285","article-title":"Fed-ensemble: Improving generalization through model ensembling in federated learning","author":"shi","year":"2021","journal-title":"arXiv 2107 10663"},{"key":"ref181","first-page":"1","article-title":"The nonparanormal: Semiparametric estimation of high-dimensional undirected graphs","volume":"10","author":"liu","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref284","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-69250-1"},{"key":"ref180","article-title":"Real-time edge intelligence in the making: A collaborative learning framework via federated meta-learning","author":"lin","year":"2020","journal-title":"arXiv 2001 03229"},{"key":"ref283","first-page":"1000","article-title":"Communication-efficient distributed optimization using an approximate newton-type method","volume":"32","author":"shamir","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref350","year":"2019","journal-title":"Federated Learning The Future of Distributed Machine Learning"},{"key":"ref282","first-page":"4567","article-title":"First order generative adversarial networks","author":"seward","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref281","article-title":"Minimizing finite sums with the stochastic average gradient","author":"schmidt","year":"2013","journal-title":"arXiv 1309 2388"},{"key":"ref185","first-page":"5393","article-title":"Adam with bandit sampling for deep learning","author":"liu","year":"2020","journal-title":"Proc NeurIPS"},{"key":"ref280","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2021.3056751"},{"key":"ref184","first-page":"5393","article-title":"Stein variational gradient descent: A general purpose Bayesian inference algorithm","author":"liu","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2013.2287101"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1115\/1.4024661"},{"key":"ref189","article-title":"The functional neural process","author":"louizos","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2018.11.072"},{"key":"ref187","article-title":"Trojaning attack on neural networks","author":"liu","year":"2017"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.2975189"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-020-00308-0"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2017.1285773"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2986024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2018.01.007"},{"key":"ref20","article-title":"The power of synergy in differential privacy: Combining a small curator with local randomizers","author":"beimel","year":"2019","journal-title":"arXiv 1912 08951"},{"key":"ref348","doi-asserted-by":"publisher","DOI":"10.1109\/BigData50022.2020.9378043"},{"key":"ref349","first-page":"39","article-title":"Enabling industrial Internet of Things (IIoT) towards an emerging smart energy system","volume":"1","author":"zhang","year":"2018","journal-title":"Global energy interconnection"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2012.01.033"},{"key":"ref21","first-page":"473","article-title":"Personalized and private peer-to-peer machine learning","author":"bellet","year":"2018","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/S0378-3758(00)00179-8"},{"key":"ref344","first-page":"962","article-title":"Fairness constraints: Mechanisms for fair classification","author":"zafar","year":"2017","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref23","article-title":"Protection against reconstruction and its applications in private federated learning","author":"bhowmick","year":"2018","journal-title":"arXiv 1812 00984"},{"key":"ref345","article-title":"Improving fairness via federated learning","author":"zeng","year":"2021","journal-title":"arXiv 2110 15545"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3132747.3132769"},{"key":"ref346","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230554"},{"key":"ref278","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaa341"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2014.01.073"},{"key":"ref347","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889774"},{"key":"ref279","article-title":"Clustered federated learning: Model-agnostic distributed multi-task optimization under privacy constraints","author":"sattler","year":"2019","journal-title":"arXiv 1910 01991"},{"key":"ref50","article-title":"A closer look at few-shot classification","author":"chen","year":"2019","journal-title":"arXiv 1904 04232"},{"key":"ref293","year":"2020","journal-title":"Faulty Masks Flawed Tests China’s Quality Control Problem in Leading Global COVID-19 Fight"},{"key":"ref51","article-title":"Optimal client sampling for federated learning","author":"chen","year":"2020","journal-title":"arXiv 2010 13723"},{"key":"ref292","year":"2020","journal-title":"Why DIY 3D-Printed Face Masks and Shields Are So Risky"},{"key":"ref295","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32381-3_16"},{"key":"ref294","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9780262017091.001.0001"},{"key":"ref297","first-page":"6155","article-title":"DoubleSqueeze: Parallel stochastic gradient descent with double-pass error-compensated compression","author":"tang","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref296","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.02.008"},{"key":"ref299","doi-asserted-by":"publisher","DOI":"10.1145\/3152434.3152441"},{"key":"ref298","article-title":"Adaptive deep kernel learning","author":"tossou","year":"2019","journal-title":"arXiv 1905 12131"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3196909"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.2017.1383310"},{"key":"ref156","article-title":"Learning task grouping and overlap in multi-task learning","author":"kumar","year":"2012","journal-title":"arXiv 1206 6417"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/WorldS450073.2020.9210355"},{"key":"ref150","article-title":"Federated learning: Strategies for improving communication efficiency","author":"kone?n\u00fd","year":"2016","journal-title":"arXiv 1610 05492"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2017.2717190"},{"key":"ref291","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2016.1192302"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2987482"},{"key":"ref290","doi-asserted-by":"publisher","DOI":"10.2307\/2297484"},{"key":"ref146","author":"koller","year":"2009","journal-title":"Probabilistic Graphical Models Principles and Techniques"},{"key":"ref147","article-title":"Decentralized deep learning with arbitrary communication compression","author":"koloskova","year":"2019","journal-title":"arXiv 1907 09356"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1214\/10-AOS825"},{"key":"ref149","article-title":"Federated optimization: Distributed machine learning for on-device intelligence","author":"kone?n\u00fd","year":"2016","journal-title":"arXiv 1610 02527"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1137\/1.9780898718768"},{"key":"ref289","article-title":"Prototypical networks for few-shot learning","author":"snell","year":"2017","journal-title":"arXiv 1703 05175"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-018-1303-3"},{"key":"ref57","year":"2020","journal-title":"12-Year-Old Boy 3D Prints Masks for Frontline Workers"},{"key":"ref56","year":"2020","journal-title":"Ford Temporarily Closes Two Plants After Three Workers Test Positive for Coronavirus"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2018436.2018448"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1002\/qre.2077"},{"key":"ref53","article-title":"Client selection in federated learning: Convergence analysis and power-of-choice selection strategies","author":"jee cho","year":"2020","journal-title":"arXiv 2010 01243"},{"key":"ref52","article-title":"Targeted backdoor attacks on deep learning systems using data poisoning","author":"chen","year":"2017","journal-title":"arXiv 1712 05526"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/431047"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2020.106879"},{"key":"ref166","author":"leurent","year":"2018","journal-title":"The Next Economic Growth Engine Scaling Fourth Industrial Revolution Technologies in Production"},{"key":"ref165","year":"2019","journal-title":"Declining Price of IoT Sensors Means Greater Use in Manufacturing"},{"key":"ref164","year":"2019","journal-title":"With Predictive Maintenance Operators Seek Improved Uptime"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2014.2320133"},{"key":"ref162","article-title":"Oort: Efficient federated learning via guided participant selection","author":"lai","year":"2020","journal-title":"arXiv 2010 06081"},{"key":"ref161","first-page":"273","article-title":"Sol: A federated execution engine for fast distributed computation over slow networks","author":"lai","year":"2020","journal-title":"Proc USENIX NSDI"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctv7h0rwr"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2020.102830"},{"key":"ref3","article-title":"Federated learning based on dynamic regularization","author":"acar","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2021.3069111"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3013541"},{"key":"ref8","article-title":"Federated learning with personalization layers","author":"ghuhan arivazhagan","year":"2019","journal-title":"arXiv 1912 00818"},{"key":"ref159","article-title":"Uncertainty in multitask transfer learning","author":"lacoste","year":"2018","journal-title":"arXiv 1806 07528"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.2016.1172027"},{"key":"ref7","year":"2019","journal-title":"Designing for Privacy"},{"key":"ref157","article-title":"Implementing the smart factory: New perspectives for driving value","author":"laaper","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2010.05.010"},{"key":"ref158","article-title":"Deep prior","author":"lacoste","year":"2017","journal-title":"arXiv 1712 05016"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.2015.1096827"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TR.2016.2611625"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140448"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1080\/24725854.2019.1628374"},{"key":"ref42","article-title":"FedBE: Making Bayesian model ensemble applicable to federated learning","author":"chen","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref41","first-page":"2722","article-title":"Stochastic gradient descent in correlated settings: A study on Gaussian processes","author":"chen","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K19-1012"},{"key":"ref43","article-title":"Federated learning of out-of-vocabulary words","author":"chen","year":"2019","journal-title":"arXiv 1903 10635"},{"key":"ref320","year":"2019","journal-title":"AI Chips for Self Driving Cars Will a Be 10 Billion Market by 2024"},{"key":"ref321","doi-asserted-by":"publisher","DOI":"10.1002\/asmb.2019"},{"key":"ref73","first-page":"2153","article-title":"On the Nyström method for approximating a Gram matrix for improved kernel-based learning","volume":"6","author":"drineas","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref72","first-page":"395","article-title":"PCC: Re-architecting congestion control for consistent high performance","author":"dong","year":"2015","journal-title":"Proc USENIX NSDI"},{"key":"ref71","author":"dolezal","year":"2020","journal-title":"3D Printed Face Shields for Medics and Professionals—Join Us!"},{"key":"ref70","first-page":"21394","article-title":"Personalized federated learning with Moreau envelopes","author":"dinh","year":"2020","journal-title":"Proc 34th Conf Neural Inf Process Syst"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.mechatronics.2017.09.002"},{"key":"ref318","doi-asserted-by":"publisher","DOI":"10.1145\/2486001.2486020"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD46524.2019.00038"},{"key":"ref317","volume":"2","author":"k williams","year":"2006","journal-title":"Gaussian Processes for Machine Learning"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s00211-010-0331-6"},{"key":"ref316","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCOUTCOMES.121.007858"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611976700.21"},{"key":"ref315","first-page":"681","article-title":"Bayesian learning via stochastic gradient Langevin dynamics","author":"welling","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn (ICML)"},{"key":"ref314","article-title":"Deloitte and mapi smart factory study: Capturing value through the digital journey","author":"wellener","year":"2019"},{"key":"ref313","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2018.03.013"},{"key":"ref78","article-title":"Towards a neural statistician","author":"edwards","year":"2017","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref312","article-title":"Federated learning with differential privacy: Algorithms and performance analysis","author":"wei","year":"2019","journal-title":"arXiv 1911 00222"},{"key":"ref79","year":"2020","journal-title":"U S Energy Information Administration U S Energy Facts Explained"},{"key":"ref311","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"ref319","doi-asserted-by":"publisher","DOI":"10.7326\/M18-1376"},{"key":"ref310","doi-asserted-by":"publisher","DOI":"10.1197\/jamia.M3191"},{"key":"ref60","year":"2019","journal-title":"Google’s Project Nightingale Gathers Personal Health Data on Millions of Americans"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.promfg.2018.07.132"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-007-0170-8"},{"key":"ref63","author":"culver","year":"2020","journal-title":"3D Printing Enthusiasts Are Working From Home to Help Hospitals Fight Coronavirus"},{"key":"ref305","doi-asserted-by":"publisher","DOI":"10.1080\/24725854.2021.1875520"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3057446"},{"key":"ref304","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.117068"},{"key":"ref65","article-title":"Adaptive personalized federated learning","author":"deng","year":"2020","journal-title":"arXiv 2003 13461"},{"key":"ref307","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2019.1800286"},{"key":"ref66","author":"denson","year":"2014","journal-title":"Electronic Parts Reliability Data 2014"},{"key":"ref306","article-title":"Federated evaluation of on-device personalization","author":"wang","year":"2019","journal-title":"arXiv 1910 10252"},{"key":"ref67","article-title":"Learning with privacy at scale","year":"2017","journal-title":"Mach Learn Appl"},{"key":"ref301","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref68","first-page":"3571","article-title":"Collecting telemetry data privately","author":"ding","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref300","article-title":"Meta-learning: A survey","author":"vanschoren","year":"2018","journal-title":"arXiv 1810 03548"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389711"},{"key":"ref303","article-title":"Federated learning with matched averaging","author":"wang","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref302","year":"2019","journal-title":"The federated future is ready for shipping"},{"key":"ref309","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2015.04.012"},{"key":"ref308","article-title":"Bayesian meta sampling for fast uncertainty adaptation","author":"wang","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1145\/3376897.3377862"},{"key":"ref198","article-title":"Towards deep learning models resistant to adversarial attacks","author":"madry","year":"2017","journal-title":"arXiv 1706 06083"},{"key":"ref199","author":"mahar","year":"2011","journal-title":"Nonelectronic Parts Reliability Data 2011"},{"key":"ref193","article-title":"Threats to federated learning: A survey","author":"lyu","year":"2020","journal-title":"arXiv 2003 02133"},{"key":"ref194","first-page":"4222","article-title":"Variational implicit processes","author":"ma","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref195","doi-asserted-by":"crossref","first-page":"164","DOI":"10.4236\/jcc.2015.35021","article-title":"Internet of Things (IoT): A literature review","volume":"3","author":"madakam","year":"2015","journal-title":"J Comput Commun"},{"key":"ref196","first-page":"13153","article-title":"A simple baseline for Bayesian uncertainty in deep learning","volume":"32","author":"maddox","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref95","article-title":"Neural processes","author":"garnelo","year":"2018","journal-title":"arXiv 1807 01622"},{"key":"ref94","first-page":"1704","article-title":"Conditional neural processes","author":"garnelo","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2810121"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1115\/1.4041833"},{"key":"ref191","article-title":"Real-world image datasets for federated learning","author":"luo","year":"2019","journal-title":"arXiv 1910 11089"},{"key":"ref92","volume":"1","author":"friedman","year":"2001","journal-title":"The Elements of Statistical Learning"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.3390\/math9010019"},{"key":"ref91","article-title":"Assessment of demand response and advanced metering","author":"foster","year":"2017"},{"key":"ref342","article-title":"GIFAIR-FL: An approach for group and individual fairness in federated learning","author":"yue","year":"2021","journal-title":"arXiv 2108 02741"},{"key":"ref90","author":"fitzgerald","year":"2016","journal-title":"General Motors Relies on IoT to Anticipate Customers Needs"},{"key":"ref343","first-page":"7252","article-title":"Bayesian nonparametric federated learning of neural networks","author":"yurochkin","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref340","article-title":"The Renyi Gaussian process: Towards improved generalization","author":"yue","year":"2019","journal-title":"arXiv 1910 06990"},{"key":"ref341","article-title":"Variational inference of joint models using multivariate Gaussian convolution processes","author":"yue","year":"2019","journal-title":"arXiv 1903 03867"},{"key":"ref336","article-title":"Salvaging federated learning by local adaptation","author":"yu","year":"2020","journal-title":"arXiv 2002 04758"},{"key":"ref335","doi-asserted-by":"publisher","DOI":"10.1080\/0740817X.2016.1204489"},{"key":"ref334","first-page":"7343","article-title":"Bayesian model-agnostic meta-learning","author":"yoon","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref333","doi-asserted-by":"publisher","DOI":"10.1214\/13-AOAS666"},{"key":"ref98","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref99","year":"2019","journal-title":"Your chats stay private while Messages improves suggestions"},{"key":"ref339","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2205006"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1145\/3386367.3433030"},{"key":"ref338","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/asm018"},{"key":"ref97","first-page":"1","article-title":"Multi-task sparse structure learning with Gaussian copula models","volume":"17","author":"gon\u00e7alves","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref337","first-page":"5332","article-title":"Federated accelerated stochastic gradient descent","author":"yuan","year":"2020","journal-title":"Proc 34th Conf Neural Inf Process Syst"},{"key":"ref82","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":"ref81","year":"2021","journal-title":"U S Energy Information Administration Consumption and Efficiency"},{"key":"ref84","year":"2020","journal-title":"3D Printing in FDA’Ts Rapid Response to COVID-19"},{"key":"ref83","article-title":"COVID-ResNet: A deep learning framework for screening of COVID19 from radiographs","author":"farooq","year":"2020","journal-title":"arXiv 2003 14395"},{"key":"ref330","article-title":"Parallel distributed logistic regression for vertical federated learning without third-party coordinator","author":"yang","year":"2019","journal-title":"arXiv 1911 09824"},{"key":"ref80","year":"2020","journal-title":"Today in Energy U S EnergyInformation Administration"},{"key":"ref331","article-title":"Applied federated learning: Improving Google keyboard query suggestions","author":"yang","year":"2018","journal-title":"arXiv 1812 02903"},{"key":"ref332","article-title":"The unusual effectiveness of averaging in GAN training","author":"yaz","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLANT50963.2020.9355973"},{"key":"ref323","article-title":"Fast-convergent federated learning with adaptive weighting","author":"wu","year":"2020","journal-title":"arXiv 2012 00661"},{"key":"ref322","volume":"552","author":"wu","year":"2011","journal-title":"Experiments Planning Analysis and Optimization"},{"key":"ref325","doi-asserted-by":"publisher","DOI":"10.1080\/03052150902852999"},{"key":"ref324","article-title":"Meta-learning autoencoders for few-shot prediction","author":"wu","year":"2018","journal-title":"arXiv 1807 09912"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783311"},{"key":"ref327","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1109\/TEC.2013.2295301","article-title":"Condition monitoring of wind power system with nonparametric regression analysis","volume":"29","author":"yampikulsakul","year":"2014","journal-title":"IEEE Trans Energy Convers"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.20485\/jsaeijae.9.3_158"},{"key":"ref326","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3031503"},{"key":"ref87","author":"field","year":"2000","journal-title":"COVID-19 How Quickly Can Manufacturing Respond to the Surge in Demand?"},{"key":"ref329","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"ref88","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref328","first-page":"495","article-title":"Learning in situ: A randomized experiment in video streaming","author":"yan","year":"2020","journal-title":"Proc USENIX NSDI"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0803205106"},{"key":"ref101","article-title":"Meta-learning probabilistic inference for prediction","author":"gordon","year":"2018","journal-title":"arXiv 1805 09921"},{"key":"ref100","year":"2021","journal-title":"Google"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1561\/9781680837896"},{"key":"ref203","article-title":"Three approaches for personalization with applications to federated learning","author":"mansour","year":"2020","journal-title":"arXiv 2002 10619"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"ref201","article-title":"Renewable electricity futures study. executive summary","author":"mai","year":"2012"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1016\/j.compenvurbsys.2017.07.006"},{"key":"ref207","article-title":"The age of analytics: Competing in a data-driven world","author":"mckinsey","year":"2016"},{"key":"ref208","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2017","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2017.01.004"},{"key":"ref206","article-title":"Efficient large-scale distributed training of conditional maximum entropy models","volume":"22","author":"mcdonald","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref211","author":"meeker","year":"1998","journal-title":"Statistical Methods for Reliability Data"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2020.117205"},{"key":"ref212","year":"2019","journal-title":"2019 manufacturing trends report"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2019.01.012"},{"key":"ref214","first-page":"4615","article-title":"Agnostic federated learning","volume":"97","author":"mohri","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref215","year":"2017","journal-title":"3-D Printing Gets a Turbo Boost From U-M Technology"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2017.2682499"},{"key":"ref217","first-page":"2554","article-title":"Meta networks","author":"munkhdalai","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.3390\/su10103491"},{"key":"ref219","first-page":"2574","article-title":"Radaptive sampling probabilities for non-smooth optimizatio","author":"namkoong","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2017.06.066"},{"key":"ref222","first-page":"1280","article-title":"PAC-Bayesian meta-learning with implicit prior","volume":"210","author":"nguyen","year":"2018","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.2172\/1508212"},{"key":"ref229","year":"2021","journal-title":"Climate Change Global Temperature"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1080\/24725854.2017.1299955"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900461"},{"key":"ref226","article-title":"On first-order meta-learning algorithms","author":"nichol","year":"2018","journal-title":"arXiv 1803 02999"},{"key":"ref225","article-title":"On first-order meta-learning algorithms","author":"nichol","year":"2018","journal-title":"arXiv 1803 02999"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/WF-IoT48130.2020.9221089"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2018.0064"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2020.110450"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2020.2965444"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.3390\/atmos10120727"},{"key":"ref124","article-title":"Averaging weights leads to wider optima and better generalization","author":"izmailov","year":"2018","journal-title":"arXiv 1803 05407"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230574"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761187"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1145\/3349614.3356026"},{"key":"ref133","article-title":"Advances and open problems in federated learning","author":"kairouz","year":"2019","journal-title":"arXiv 1912 04977"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2940820"},{"key":"ref131","article-title":"Improving federated learning personalization via model agnostic meta learning","author":"jiang","year":"2019","journal-title":"arXiv 1909 12488"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.2018.1451390"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2019.101880"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1126\/science.abg4924"},{"key":"ref230","article-title":"Entity resolution and federated learning get a federated resolution","author":"nock","year":"2018","journal-title":"arXiv 1803 04035"},{"key":"ref231","year":"2009","journal-title":"Office for Civil Rights"},{"key":"ref239","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref238","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref235","year":"2021","journal-title":"Welcome to Onstar"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.3390\/inventions3030056"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2020.109861"},{"key":"ref236","year":"2009","journal-title":"OREDA Offshore Reliability Data Handbook"},{"key":"ref136","first-page":"521","article-title":"Learning with whom to share in multi-task feature learning","author":"kang","year":"2011","journal-title":"Proc ICML"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1198\/TECH.2011.08132"},{"key":"ref138","first-page":"2525","article-title":"Not all samples are created equal: Deep learning with importance sampling","author":"katharopoulos","year":"2018","journal-title":"Proc 35 th Int Conf Mach Learn"},{"key":"ref137","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","author":"karimireddy","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(21)00722-4"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1186\/s13174-015-0029-1"},{"key":"ref141","article-title":"Attentive neural processes","author":"kim","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref142","year":"2019","journal-title":"Nvidia Clara Federated Learning to Deliver AI to Hospitals While Protecting Patient Data"},{"key":"ref143","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2019.04.008"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref1","year":"2020","journal-title":"Ford SYNC"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1002\/net.21736"},{"key":"ref241","article-title":"Bayesian meta-learning for the few-shot setting via deep kernels","author":"patacchiola","year":"2019","journal-title":"arXiv 1910 05199"},{"key":"ref242","first-page":"16108","article-title":"Bayesian meta-learning for the few-shot setting via deep kernels","author":"patacchiola","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref243","first-page":"7057","article-title":"FedSplit: An algorithmic framework for fast federated optimization","author":"pathak","year":"2020","journal-title":"Proc 34th Conf Neural Inf Process Syst"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1137\/0103003"},{"key":"ref240","first-page":"631","article-title":"Learning large-scale Poisson dag models based on overdispersion scoring","author":"park","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref248","doi-asserted-by":"publisher","DOI":"10.1111\/1475-6773.12654"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2019.2907440"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2015.2413453"},{"key":"ref245","volume":"29","author":"pearl","year":"2000","journal-title":"Causality Models Reasoning and Inference"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2016.1211016"},{"key":"ref109","article-title":"Federated learning for ranking browser history suggestions","author":"hartmann","year":"2019","journal-title":"arXiv 1911 11807"},{"key":"ref108","article-title":"Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption","author":"hardy","year":"2017","journal-title":"arXiv 1711 10677"},{"key":"ref107","first-page":"3315","article-title":"Equality of opportunity in supervised learning","volume":"29","author":"hardt","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref106","article-title":"Federated learning for mobile keyboard prediction","author":"hard","year":"2018","journal-title":"arXiv 1811 03604"},{"key":"ref105","article-title":"Federated learning of a mixture of global and local models","author":"hanzely","year":"2020","journal-title":"arXiv 2002 05516"},{"key":"ref104","article-title":"Recasting gradient-based meta-learning as hierarchical Bayes","author":"grant","year":"2018","journal-title":"arXiv 1801 08930"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1201\/9780367815493"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1007\/BF02759761"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ETFA.2016.7733661"},{"key":"ref112","article-title":"Meta-learning in neural networks: A survey","author":"hospedales","year":"2020","journal-title":"arXiv 2004 05439"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1201\/b18401"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12314"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-007-5040-8"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1080\/00031305.2019.1700163"},{"key":"ref255","article-title":"Language models are unsupervised multitask learners","author":"radford","year":"2019","journal-title":"Proc OpenAI"},{"key":"ref252","first-page":"64","article-title":"How smart, connected products are transforming competition","volume":"92","author":"porter","year":"2014","journal-title":"Harvard Bus Rev"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787505"},{"key":"ref257","article-title":"Federated learning for emoji prediction in a mobile keyboard","author":"ramaswamy","year":"2019","journal-title":"arXiv 1906 04329"},{"key":"ref256","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3030072"},{"key":"ref10","year":"2019","journal-title":"What is aws"},{"key":"ref259","first-page":"398","article-title":"Minimax-optimal rates for sparse additive models over kernel classes via convex programming","volume":"13","author":"raskutti","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref11","year":"2021","journal-title":"Amazon Web Services"},{"key":"ref258","first-page":"1","article-title":"A statistical perspective on randomized sketching for ordinary least-squares","volume":"17","author":"raskutti","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref12","year":"2018","journal-title":"Microsoft How does Azure RMS work?"},{"key":"ref13","first-page":"1179","article-title":"Consistency of the group lasso and multiple kernel learning","volume":"9","author":"bach","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref14","first-page":"2938","article-title":"How to backdoor federated learning","author":"bagdasaryan","year":"2020","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref15","article-title":"Rényi fair inference","author":"baharlouei","year":"2020","journal-title":"arXiv 1906 12005"},{"key":"ref16","first-page":"463","article-title":"Rademacher and Gaussian complexities: Risk bounds and structural results","volume":"3","author":"peter bartlett","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref118","article-title":"LoAdaBoost: Loss-based AdaBoost federated machine learning with reduced computational complexity on IID and non-IID intensive care data","author":"huang","year":"2018","journal-title":"arXiv 1811 12629"},{"key":"ref17","article-title":"Discriminative k-shot learning using probabilistic models","author":"bauer","year":"2017","journal-title":"arXiv 1706 00326"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0230706"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/jmmp1020015"},{"key":"ref19","article-title":"How to achieve and sustain the impact of digital manufacturing at scale","author":"behrendt","year":"2017"},{"key":"ref119","article-title":"Fairness and accuracy in federated learning","author":"huang","year":"2020","journal-title":"arXiv 2012 10069"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2020.2986269"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.3390\/en13020494"},{"key":"ref116","article-title":"FedMGDA+: Federated learning meets multi-objective optimization","author":"hu","year":"2020","journal-title":"arXiv 2006 11489"},{"key":"ref115","first-page":"269","article-title":"Focus: Querying large video datasets with low latency and low cost","author":"hsieh","year":"2018","journal-title":"Proc USENIX OSDI"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1080\/00401706.2013.869263"},{"key":"ref121","first-page":"6659","article-title":"Training neural networks using features replay","author":"huo","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017858"},{"key":"ref123","year":"2020","journal-title":"Can 3D Printing Plug the Coronavirus Equipment Gap?"},{"key":"ref260","first-page":"335","article-title":"Early stopping and non-parametric regression: An optimal data-dependent stopping rule","volume":"15","author":"raskutti","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref261","author":"rasmussen","year":"2006","journal-title":"Gaussian Processes for Machine Learning"},{"key":"ref262","article-title":"Amortized Bayesian meta-learning","author":"ravi","year":"2019","journal-title":"Proc ICLR (Poster)"},{"key":"ref263","doi-asserted-by":"publisher","DOI":"10.5220\/0010243202360242"},{"key":"ref264","doi-asserted-by":"publisher","DOI":"10.1214\/11-EJS631"},{"key":"ref265","article-title":"Adaptive methods for nonconvex optimization","author":"reddi","year":"2018","journal-title":"Proc 32nd Conf Neural Inf Process Syst (NIPS)"},{"key":"ref266","article-title":"Adaptive federated optimization","author":"reddi","year":"2021","journal-title":"Proc Int Conf Learn Represent"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6287639\/9312710\/9611259-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09611259.pdf?arnumber=9611259","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:53:39Z","timestamp":1649444019000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9611259\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":361,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3127448","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}