{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T06:00:21Z","timestamp":1777874421859,"version":"3.51.4"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Major Basic Research Program of Shandong Provincial Natural Science Foundation","award":["ZR2025ZD18"],"award-info":[{"award-number":["ZR2025ZD18"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20244"],"award-info":[{"award-number":["U24A20244"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Netw."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/ton.2026.3686661","type":"journal-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T19:57:59Z","timestamp":1776974279000},"page":"4809-4824","source":"Crossref","is-referenced-by-count":0,"title":["Byzantine-Resilient Federated Learning Under Heterogeneity and Heavy Tails"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6750-1190","authenticated-orcid":false,"given":"Youming","family":"Tao","sequence":"first","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Technische Universität Berlin, Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8328-2303","authenticated-orcid":false,"given":"Zuyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Engineering and Applied Science, The George Washington University, Washington, DC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4908-0243","authenticated-orcid":false,"given":"Di","family":"Wang","sequence":"additional","affiliation":[{"name":"Division of Computer, Electrical and Mathematical Sciences and Engineering, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6835-5981","authenticated-orcid":false,"given":"Dongxiao","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5912-4647","authenticated-orcid":false,"given":"Xiuzhen","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1989-1750","authenticated-orcid":false,"given":"Falko","family":"Dressler","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Technische Universität Berlin, Berlin, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"McMahan"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.2986024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3075439"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.hcc.2021.100008"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/357172.357176"},{"key":"ref6","first-page":"5650","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","author":"Yin"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3625558"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3055399.3055491"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3465084.3467902"},{"key":"ref10","article-title":"Byzantine-robust learning on heterogeneous datasets via bucketing","volume-title":"Proc. 10th Int. Conf. Learn. Represent. (ICLR)","author":"Karimireddy"},{"key":"ref11","first-page":"1232","article-title":"Fixing by mixing: A recipe for optimal Byzantine ML under heterogeneity","volume-title":"Proc. 26th Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"Allouah"},{"key":"ref12","article-title":"On large-cohort training for federated learning","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Charles"},{"key":"ref13","article-title":"Taming fat-tailed (\u2019heavier-tailed\u2019 with potentially infinite variance) noise in federated learning","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Yang"},{"key":"ref14","article-title":"High-probability bounds for non-convex stochastic optimization with heavy tails","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Cutkosky"},{"key":"ref15","first-page":"261","article-title":"Fall of empires: Breaking Byzantine-tolerant SGD by inner product manipulation","volume-title":"Proc. 35th Uncertainty Artif. Intell. Conf.","author":"Xie"},{"key":"ref16","first-page":"8632","article-title":"A little is enough: Circumventing defenses for distributed learning","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst. (NeurIPS)","volume":"32","author":"Baruch"},{"key":"ref17","article-title":"Byzantine-resilient non-convex stochastic gradient descent","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Allen-Zhu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2021.24498"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3153135"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3154503"},{"key":"ref21","first-page":"560","article-title":"SignSGD: Compressed optimisation for non-convex problems","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Bernstein"},{"key":"ref22","article-title":"Stochastic-sign SGD for federated learning with theoretical guarantees","author":"Jin","year":"2021","journal-title":"arXiv:2002.10940"},{"key":"ref23","first-page":"118","article-title":"Machine learning with adversaries: Byzantine tolerant gradient descent","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst. (NIPS)","volume":"30","author":"Blanchard"},{"key":"ref24","article-title":"The hidden vulnerability of distributed learning in byzantium","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","author":"Mhamdi"},{"key":"ref25","first-page":"5827","article-title":"A tail-index analysis of stochastic gradient noise in deep neural networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","author":"\u015eim\u015fekli"},{"key":"ref26","first-page":"15383","article-title":"Why are adaptive methods good for attention models","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Zhang"},{"key":"ref27","first-page":"15042","article-title":"Stochastic optimization with heavy-tailed noise via accelerated gradient clipping","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Gorbunov"},{"key":"ref28","first-page":"3964","article-title":"The heavy-tail phenomenon in SGD","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","author":"G\u00fcrb\u00fczbalaban"},{"key":"ref29","article-title":"First exit time analysis of stochastic gradient descent under heavy-tailed gradient noise","volume-title":"Proc. 33rd Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Nguyen"},{"key":"ref30","first-page":"8970","article-title":"Fractional underdamped Langevin dynamics: Retargeting SGD with momentum under heavy-tailed gradient noise","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"\u015eim\u015fekli"},{"key":"ref31","first-page":"4262","article-title":"Multiplicative noise and heavy tails in stochastic optimization","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","author":"Hodgkinson"},{"key":"ref32","article-title":"Convergence rates of stochastic gradient descent under infinite noise variance","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Wang"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2023.3257510"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref35","article-title":"Variance reduction is an antidote to Byzantines: Better rates, weaker assumptions and communication compression as a cherry on the top","volume-title":"Proc. 11th Int. Conf. Learn. Represent. (ICLR)","author":"Gorbunov"},{"key":"ref36","first-page":"6246","article-title":"Byzantine machine learning made easy by resilient averaging of momentums","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"162","author":"Farhadkhani"},{"key":"ref37","article-title":"Distributed momentum for Byzantine-resilient stochastic gradient descent","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Mhamdi"},{"key":"ref38","first-page":"5311","article-title":"Learning from history for Byzantine robust optimization","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Karimireddy"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2017.64"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref41","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"}],"container-title":["IEEE Transactions on Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10723154\/11317935\/11494133.pdf?arnumber=11494133","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:46:58Z","timestamp":1777578418000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11494133\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/ton.2026.3686661","relation":{},"ISSN":["2998-4157"],"issn-type":[{"value":"2998-4157","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}