{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T10:34:13Z","timestamp":1776335653761,"version":"3.51.2"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CIF-1703678"],"award-info":[{"award-number":["CIF-1703678"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Machine Learning for Wireless Networking Systems","award":["2002821"],"award-info":[{"award-number":["2002821"]}]},{"name":"Ph.D. Students at UC Berkeley"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Inform. Theory"],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1109\/tit.2022.3192506","type":"journal-article","created":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T19:31:58Z","timestamp":1658259118000},"page":"8076-8091","source":"Crossref","is-referenced-by-count":406,"title":["An Efficient Framework for Clustered Federated Learning"],"prefix":"10.1109","volume":"68","author":[{"given":"Avishek","family":"Ghosh","sequence":"first","affiliation":[{"name":"Halicioglu Data Science Institute, UC San Diego, La Jolla, CA, USA"}]},{"given":"Jichan","family":"Chung","sequence":"additional","affiliation":[{"name":"EECS Department, UC Berkeley, Berkeley, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2358-0816","authenticated-orcid":false,"given":"Dong","family":"Yin","sequence":"additional","affiliation":[{"name":"DeepMind, Mountain View, CA, USA"}]},{"given":"Kannan","family":"Ramchandran","sequence":"additional","affiliation":[{"name":"EECS Department, UC Berkeley, Berkeley, CA, USA"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2018.2800663"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1214\/16-AOS1435"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1364\/AO.21.002758"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2018.2864276"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-4651-1_7"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1109\/TPAMI.2005.102","article-title":"Effective Gaussian mixture learning for video background subtraction","volume":"27","author":"lee","year":"2005","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref37","article-title":"Solving a mixture of many random linear equations by tensor decomposition and alternating minimization","author":"yi","year":"2016","journal-title":"arXiv 1608 05749"},{"key":"ref36","first-page":"704","article-title":"Ten steps of EM suffice for mixtures of two Gaussians","author":"daskalakis","year":"2017","journal-title":"Proc Conf Learn Theory"},{"key":"ref35","first-page":"2796","article-title":"Phase retrieval using alternating minimization","author":"netrapalli","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1364\/JOSAA.7.000394"},{"key":"ref28","article-title":"Federated mixture of experts","author":"reisser","year":"2021","journal-title":"arXiv 2107 06724"},{"key":"ref27","first-page":"1","article-title":"Federated learning using mixture of experts","author":"zec","year":"2020","journal-title":"Proc ICLR Conf"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1996.8.1.129"},{"key":"ref2","article-title":"Federated optimization: Distributed machine learning for on-device intelligence","author":"kone?n\u00fd","year":"2016","journal-title":"arXiv 1610 02527"},{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2017","journal-title":"Proc 20th Int Conf Artif Intell Statist"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011544"},{"key":"ref22","first-page":"1","article-title":"On the convergence of FedAvg on non-IID data","author":"li","year":"2020","journal-title":"Proc Int Conf Learn Representations (ICLR)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2944481"},{"key":"ref24","article-title":"Personalized federated learning: A meta-learning approach","author":"fallah","year":"2020","journal-title":"arXiv 2002 07948"},{"key":"ref23","first-page":"4615","article-title":"Agnostic federated learning","author":"mohri","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","article-title":"FedGroup: Efficient clustered federated learning via decomposed data-driven measure","author":"duan","year":"2020","journal-title":"arXiv 2010 06870"},{"key":"ref25","article-title":"Federated meta-learning with fast convergence and efficient communication","author":"chen","year":"2018","journal-title":"arXiv 1802 07876"},{"key":"ref50","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref51","first-page":"6467","article-title":"Gradient episodic memory for continual learning","author":"lopez-paz","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1214\/ECP.v18-2865"},{"key":"ref55","article-title":"Introduction to the non-asymptotic analysis of random matrices","author":"vershynin","year":"2010","journal-title":"arXiv 1011 3027"},{"key":"ref54","first-page":"19586","article-title":"An efficient framework for clustered federated learning","volume":"33","author":"ghosh","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref53","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"james","year":"2017","journal-title":"Proc Nat Acad Sci USA"},{"key":"ref52","article-title":"An empirical investigation of catastrophic forgetting in gradient-based neural networks","author":"goodfellow","year":"2013","journal-title":"arXiv 1312 6211"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007379606734"},{"key":"ref11","article-title":"LEAF: A benchmark for federated settings","author":"caldas","year":"2018","journal-title":"arXiv 1812 01097"},{"key":"ref40","first-page":"1093","article-title":"Alternating minimization converges super-linearly for mixed linear regression","author":"ghosh","year":"2020","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/BF01897167"},{"key":"ref13","first-page":"721","article-title":"Learning mixtures of linear classifiers","author":"sun","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","first-page":"2595","article-title":"Parallelized stochastic gradient descent","author":"zinkevich","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref15","first-page":"693","article-title":"Hogwild: A lock-free approach to parallelizing stochastic gradient descent","author":"recht","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2640087.2644155"},{"key":"ref17","article-title":"Federated learning for mobile keyboard prediction","author":"hard","year":"2018","journal-title":"arXiv 1811 03604"},{"key":"ref18","article-title":"Federated learning with non-IID data","author":"zhao","year":"2018","journal-title":"arXiv 1806 00582"},{"key":"ref19","article-title":"Federated optimization in heterogeneous networks","author":"li","year":"2018","journal-title":"arXiv 1812 06127"},{"key":"ref4","first-page":"4424","article-title":"Federated multi-task learning","author":"smith","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","author":"mcmahan","year":"2017","journal-title":"Federated learning Collaborative machine learning without centralized training data"},{"key":"ref6","article-title":"Improving federated learning personalization via model agnostic meta learning","author":"jiang","year":"2019","journal-title":"arXiv 1909 12488"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3015958"},{"key":"ref8","first-page":"291","article-title":"Recommender systems for large-scale e-commerce: Scalable neighborhood formation using clustering","volume":"1","author":"sarwar","year":"2002","journal-title":"Proc Int Conf Comput Inf Technol"},{"key":"ref7","article-title":"Three approaches for personalization with applications to federated learning","author":"mansour","year":"2020","journal-title":"arXiv 2002 10619"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref9","first-page":"33","article-title":"Clustering approach for hybrid recommender system","author":"li","year":"2003","journal-title":"Proc IEEE\/WIC Int Conf Web Intell (WI)"},{"key":"ref46","first-page":"6956","article-title":"Convergence of gradient EM on multi-component mixture of Gaussians","author":"yan","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","first-page":"613","article-title":"Alternating minimization for mixed linear regression","author":"yi","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref48","first-page":"165","article-title":"Optimal distributed online prediction using mini-batches","volume":"13","author":"dekel","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1017\/9781108627771"},{"key":"ref42","first-page":"1","article-title":"GIANT: Globally improved approximate Newton method for distributed optimization","author":"wang","year":"2018","journal-title":"Proc 32nd Conf Neural Inf Process Syst"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1982.1056489"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2488608.2488693"},{"key":"ref43","first-page":"18028","article-title":"Distributed Newton can communicate less and resist Byzantine workers","author":"ghosh","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/18\/9961124\/9832954-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/18\/9961124\/09832954.pdf?arnumber=9832954","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,12]],"date-time":"2022-12-12T19:12:14Z","timestamp":1670872334000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9832954\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":56,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tit.2022.3192506","relation":{},"ISSN":["0018-9448","1557-9654"],"issn-type":[{"value":"0018-9448","type":"print"},{"value":"1557-9654","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12]]}}}