{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T15:36:19Z","timestamp":1784648179147,"version":"3.55.0"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Mag."],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1109\/msp.2020.2975749","type":"journal-article","created":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T20:10:53Z","timestamp":1588363853000},"page":"50-60","source":"Crossref","is-referenced-by-count":4782,"title":["Federated Learning: Challenges, Methods, and Future Directions"],"prefix":"10.1109","volume":"37","author":[{"given":"Tian","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4083-0418","authenticated-orcid":false,"given":"Anit Kumar","family":"Sahu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ameet","family":"Talwalkar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Virginia","family":"Smith","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"8386","article-title":"Robust and communication-efficient collaborative learning","author":"reisizadeh","year":"0","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref38","article-title":"FedPAQ: A communication-efficient federated learning method with periodic averaging and quantization","author":"reisizadeh","year":"2019"},{"key":"ref33","first-page":"4615","article-title":"Agnostic federated learning","author":"mohri","year":"0","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref32","article-title":"Learning differentially private recurrent language models","author":"mcmahan","year":"0","journal-title":"Proc Int Conf Learning Representations"},{"key":"ref31","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"0","journal-title":"Proc Int Conf Artificial Intelligence Statistics"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1061318.1061322"},{"key":"ref37","first-page":"693","article-title":"Hogwild!: A lock-free approach to parallelizing stochastic gradient descent","author":"recht","year":"0","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761315"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2013.30"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.125"},{"key":"ref28","first-page":"5330","article-title":"Can decentralized algorithms outperform centralized algorithms? A case study for decentralized parallel stochastic gradient descent","author":"lian","year":"0","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref27","article-title":"On the convergence of FedAvg on non-IID data","author":"li","year":"0","journal-title":"Proc Int Conf Learning Representations"},{"key":"ref29","first-page":"1134","article-title":"Divide-and-conquer matrix factorization","author":"mackey","year":"0","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref2","article-title":"Protection against reconstruction and its applications in private federated learning","author":"bhowmick","year":"2018"},{"key":"ref1","first-page":"7564","article-title":"cpSGD: Communication-efficient and differentially-private distributed SGD","author":"agarwal","year":"0","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref20","article-title":"Communication-efficient on-device machine learning: Federated distillation and augmentation under non-IID private data","author":"jeong","year":"2018"},{"key":"ref22","article-title":"Federated learning: Strategies for improving communication efficiency","author":"konec?ny`","year":"2016"},{"key":"ref21","first-page":"5917","article-title":"Adaptive gradient-based meta-learning methods","author":"khodak","year":"0","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref24","article-title":"Differentially private meta-learning","author":"li","year":"0","journal-title":"Proc Int Conf Learning Representations"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27663-7_2"},{"key":"ref26","article-title":"Fair resource allocation in federated learning","author":"li","year":"0","journal-title":"Proc Int Conf Learning Representations"},{"key":"ref25","article-title":"Federated optimization in heterogeneous networks","author":"li","year":"0","journal-title":"Proc Conf Machine Learning and Systems"},{"key":"ref50","first-page":"5650","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","author":"yin","year":"0","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref51","first-page":"1998","article-title":"Gradient diversity: A key ingredient for scalable distributed learning","author":"yin","year":"0","journal-title":"Proc Artificial Intelligence and Statistics"},{"key":"ref55","year":"0","journal-title":"TensorFlow federated Machine learning on decentralized data"},{"key":"ref54","year":"0"},{"key":"ref53","first-page":"685","article-title":"Deep learning with elastic averaging SGD","author":"zhang","year":"0","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015693"},{"key":"ref10","first-page":"267","article-title":"The secret sharer: Evaluating and testing unintended memorization in neural networks","author":"carlini","year":"0","journal-title":"Proc Usenix Security Symp"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2018.8437887"},{"key":"ref40","article-title":"Communication-efficient distributed strongly convex stochastic optimization: Non-asymptotic rates","author":"sahu","year":"2018"},{"key":"ref12","article-title":"Variational federated multi-task learning","author":"corinzia","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/11681878_14"},{"key":"ref14","first-page":"1764","article-title":"Semi-cyclic stochastic gradient descent","author":"eichner","year":"0","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1197\/jamia.M2716"},{"key":"ref16","article-title":"Anytime Minibatch: Exploiting stragglers in online distributed optimization","author":"ferdinand","year":"0","journal-title":"Proc Int Conf Learning Representations"},{"key":"ref17","article-title":"Federated learning for mobile keyboard prediction","author":"hard","year":"2018"},{"key":"ref18","first-page":"4541","article-title":"Cola: Decentralized linear learning","author":"he","year":"0","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref19","article-title":"LoAdaBoost: Loss-based adaboost federated machine learning on medical data","author":"huang","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133982"},{"key":"ref3","first-page":"527","article-title":"Adaptive neural networks for efficient inference","volume":"70","author":"bolukbasi","year":"0","journal-title":"Proc Int Conf Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2342509.2342513"},{"key":"ref5","article-title":"Towards federated learning at scale: System design","author":"bonawitz","year":"0","journal-title":"Proc Conf Machine Learning and Systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2018.01.007"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2015.23241"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s00365-006-0663-2"},{"key":"ref9","article-title":"Expanding the reach of federated learning by reducing client resource requirements","author":"caldas","year":"2018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/DATE.2009.5090858"},{"key":"ref45","first-page":"7652","article-title":"Communication compression for decentralized training","author":"tang","year":"0","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref48","article-title":"Cooperative SGD: A unified framework for the design and analysis of communication-efficient SGD algorithms","author":"wang","year":"2018"},{"key":"ref47","first-page":"1","article-title":"ATOMO: Communication-efficient learning via atomic sparsification","author":"wang","year":"0","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref42","first-page":"4424","article-title":"Federated multi-task learning","author":"smith","year":"0","journal-title":"Proc Advances in Neural Information Processing Systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11723-8_9"},{"key":"ref44","article-title":"Local SGD converges fast and communicates little","author":"stich","year":"0","journal-title":"Proc Int Conf Learning Representations"},{"key":"ref43","first-page":"8590","article-title":"CoCoA: A general framework for communication-efficient distributed optimization","volume":"18","author":"smith","year":"2018","journal-title":"J Mach Learning Res"}],"container-title":["IEEE Signal Processing Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/79\/9084311\/09084352.pdf?arnumber=9084352","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:35:37Z","timestamp":1651073737000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9084352\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":55,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/msp.2020.2975749","relation":{},"ISSN":["1053-5888","1558-0792"],"issn-type":[{"value":"1053-5888","type":"print"},{"value":"1558-0792","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5]]}}}