{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:15:54Z","timestamp":1792786554304,"version":"4.5.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T00:00:00Z","timestamp":1654041600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF-CNS","award":["2016737"],"award-info":[{"award-number":["2016737"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Areas Inf. Theory"],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1109\/jsait.2022.3189051","type":"journal-article","created":{"date-parts":[[2022,7,11]],"date-time":"2022-07-11T15:51:14Z","timestamp":1657554674000},"page":"172-182","source":"Crossref","is-referenced-by-count":27,"title":["Peer-to-Peer Variational Federated Learning Over Arbitrary Graphs"],"prefix":"10.1109","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2916-2145","authenticated-orcid":false,"given":"Xinghan","family":"Wang","sequence":"first","affiliation":[{"name":"Computer Science and Engineering Department, University of California at San Diego, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4179-7151","authenticated-orcid":false,"given":"Anusha","family":"Lalitha","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, University of California at San Diego, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7112-1043","authenticated-orcid":false,"given":"Tara","family":"Javidi","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, University of California at San Diego, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0798-3794","authenticated-orcid":false,"given":"Farinaz","family":"Koushanfar","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, University of California at San Diego, La Jolla, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","first-page":"1727","article-title":"Streaming variational bayes","volume":"26","author":"broderick","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1214\/12-EJS675"},{"key":"ref12","first-page":"1613","article-title":"Weight uncertainty in neural networks","author":"blundell","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn Vol 37"},{"key":"ref34","author":"gal","year":"2016","journal-title":"Uncertainty in deep learning"},{"key":"ref15","first-page":"8590","article-title":"CoCoA: A general framework for communication-efficient distributed optimization","volume":"18","author":"smith","year":"2018","journal-title":"J Mach Learn Res"},{"key":"ref37","article-title":"Federated learning on non-IID data silos: An experimental study","author":"li","year":"2021","journal-title":"arXiv 2102 02079"},{"key":"ref14","first-page":"2575","article-title":"Variational dropout and the local reparameterization trick","author":"kingma","year":"2015","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1561\/9781680837896"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.2003.1238221"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2004.02.022"},{"key":"ref11","first-page":"1","article-title":"Variational continual learning","author":"nguyen","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref33","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref10","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"mcmahan","year":"2017","journal-title":"Proc Int Conf Artif Intell Stat"},{"key":"ref32","article-title":"Decentralized variational Bayesian inference","author":"campbell","year":"2014","journal-title":"arXiv 1403 7471v1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2015.2506903"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2014.6874893"},{"key":"ref17","article-title":"Don’t use large mini-batches, use local SGD","author":"lin","year":"2018","journal-title":"arXiv 1808 07217"},{"key":"ref39","author":"murphy","year":"2012","journal-title":"Machine Learning A Probabilistic Perspective"},{"key":"ref16","article-title":"Parle: Parallelizing stochastic gradient descent","author":"chaudhari","year":"2017","journal-title":"arXiv 1707 00424"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.098"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6425904"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2161027"},{"key":"ref24","article-title":"How to scale distributed deep learning?","author":"jin","year":"2016","journal-title":"arXiv 1611 04581"},{"key":"ref23","first-page":"5904","article-title":"Collaborative deep learning in fixed topology networks","volume":"30","author":"jiang","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref26","first-page":"3043","article-title":"Asynchronous decentralized parallel stochastic gradient descent","author":"lian","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2817461"},{"key":"ref20","first-page":"4848","article-title":"$d^{2}$\n: Decentralized training over decentralized data","volume":"80","author":"tang","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref42","article-title":"LEAF: A benchmark for federated settings","author":"caldas","year":"2019","journal-title":"arXiv 1812 01097"},{"key":"ref41","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"xiao","year":"2017","journal-title":"ArXiv 1708 07747"},{"key":"ref22","first-page":"5330","article-title":"Can decentralized algorithms outperform centralized algorithms? a case study for decentralized parallel stochastic gradient descent","author":"lian","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080173"},{"key":"ref43","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"arXiv 1412 6980"},{"key":"ref28","first-page":"344","article-title":"Stochastic gradient push for distributed deep learning","author":"assran","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2529285"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.874516"},{"key":"ref8","article-title":"Federated optimization: Distributed machine learning for on-device intelligence","author":"kone?n\u00fd","year":"2016","journal-title":"arXiv 1610 02527"},{"key":"ref7","article-title":"Federated learning via posterior averaging: A new perspective and practical algorithms","author":"al-shedivat","year":"2021","journal-title":"arXiv 2010 05273"},{"key":"ref9","article-title":"Federated learning: Strategies for improving communication efficiency","author":"kone?n?","year":"2016","journal-title":"arXiv 1610 05492"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2018.2837050"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2017.2690401"},{"key":"ref6","article-title":"Peer-to-peer federated learning on graphs","author":"lalitha","year":"2019","journal-title":"arXiv 1901 11173"},{"key":"ref5","first-page":"1","article-title":"Fully decentralized federated learning","author":"lalitha","year":"2018","journal-title":"Proc NeurIPS Workshop Bayesian Deep Learn"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"}],"container-title":["IEEE Journal on Selected Areas in Information Theory"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/8700143\/9953899\/9825726-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8700143\/9953899\/09825726.pdf?arnumber=9825726","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,4]],"date-time":"2023-02-04T00:06:14Z","timestamp":1675469174000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9825726\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,6]]},"references-count":43,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/jsait.2022.3189051","relation":{},"ISSN":["2641-8770"],"issn-type":[{"value":"2641-8770","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,6]]}}}