{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T15:55:28Z","timestamp":1774886128524,"version":"3.50.1"},"reference-count":94,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12371519"],"award-info":[{"award-number":["12371519"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61771013"],"award-info":[{"award-number":["61771013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Asiainfo Technologies"},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundamental Research Funds of Shanghai Jiading District"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tmc.2025.3602796","type":"journal-article","created":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T19:24:10Z","timestamp":1756236250000},"page":"1219-1235","source":"Crossref","is-referenced-by-count":1,"title":["Federated Distributionally Robust Optimization With Non-Convex Objectives: Algorithm and Analysis"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9468-1000","authenticated-orcid":false,"given":"Yang","family":"Jiao","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5983-198X","authenticated-orcid":false,"given":"Kai","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7027-7916","authenticated-orcid":false,"given":"Dongjin","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Connecticut, Storrs, CT, USA"}]}],"member":"263","reference":[{"key":"ref1","first-page":"3365","article-title":"Communication-efficient distributed learning via Lazily aggregated quantized gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2014.11.008"},{"key":"ref3","first-page":"4615","article-title":"Agnostic federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mohri"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621105"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MITP.2024.3496915"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.005.2300016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3126060"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2024.100685"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jisa.2025.104116"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2024.100697"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2494865"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3312276"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2020.10.020"},{"key":"ref15","first-page":"11220","article-title":"Federated reconstruction: Partially local federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Singhal"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-97565-4"},{"key":"ref17","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref18","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Karimireddy"},{"key":"ref19","first-page":"15111","article-title":"Distributionally robust federated averaging","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Deng"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2016.2537271"},{"key":"ref21","first-page":"1701","article-title":"Asynchronous distributed ADMM for consensus optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30557"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014739"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539231"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1137\/21M1465548"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3026619"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1030.0065"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3319657"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2023.3304624"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tmc.2025.3571023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.5802\/ojmo.15"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1090.0741"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1120.0566"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6377(99)00016-4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1137\/130925013"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s10287-015-0236-z"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.omega.2014.12.006"},{"key":"ref38","first-page":"36811","article-title":"Asynchronous distributed bilevel optimization","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Jiao"},{"key":"ref39","first-page":"78412","article-title":"Contextual stochastic bilevel optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11081-012-9198-y"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2018.08.031"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2008.171"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3050955"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/BigData50022.2020.9378161"},{"issue":"1","key":"ref45","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1007\/s10107-022-01919-z","volume":"201","author":"Xu","year":"2023","journal-title":"Math. Program."},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1038\/sj.jors.2600425"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1137\/0217049"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3730058"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685599"},{"key":"ref50","first-page":"3988","article-title":"Stochastic smoothed gradient descent ascent for federated minimax optimization","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Shen"},{"key":"ref51","first-page":"2208","article-title":"Stochastic gradient methods for distributionally robust optimization with f-divergences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Namkoong"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17050"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1287\/opre.21.5.1154"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1021\/ie200150p"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref56","volume-title":"Lectures on Modern Convex Optimization (2012)","author":"Ben-Tal","year":"2011"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-016-0998-2"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1137\/0803043"},{"key":"ref59","first-page":"214","article-title":"Wasserstein generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arjovsky"},{"key":"ref60","first-page":"6808","article-title":"Wasserstein adversarial examples via projected Sinkhorn iterations","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wong"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2022.2383"},{"key":"ref62","first-page":"675","article-title":"Universal generalization guarantees for Wasserstein distributionally robust models","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Le"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/BigData59044.2023.10386691"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2022.3216837"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10651543"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1287\/ijoc.2019.0913"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2986363"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1137\/23M1568168"},{"key":"ref69","first-page":"4880","article-title":"What is local optimality in nonconvex-nonconcave minimax optimization?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jin"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-36095-4_17"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2018.8646618"},{"key":"ref72","first-page":"6083","article-title":"On gradient descent ascent for nonconvex-concave minimax problems","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lin"},{"key":"ref73","first-page":"19683","article-title":"Federated minimax optimization: Improved convergence analyses and algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sharma"},{"key":"ref74","first-page":"11232","article-title":"Solving a class of non-convex minimax optimization in federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref75","article-title":"Federated minimax optimization with client heterogeneity","author":"Sharma","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref76","first-page":"29525","article-title":"GBA: A tuning-free approach to switch between synchronous and asynchronous training for recommendation models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Su"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2018.00075"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/AINA.2016.84"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2858933"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-16917-5_18"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/s00779-011-0415-z"},{"key":"ref82","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966039"},{"key":"ref84","first-page":"2938","article-title":"How to backdoor federated learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Bagdasaryan"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2941376"},{"key":"ref86","first-page":"16937","article-title":"Inverting gradients-how easy is it to break privacy in federated learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Geiping"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2025.3545912"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29190"},{"key":"ref89","first-page":"1","article-title":"DTZO: Distributed trilevel zeroth order learning with provable non-asymptotic convergence","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiao"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2021.3063517"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3557857"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9014329"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/GIIS56506.2022.9937034"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685514"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11275706\/11141737.pdf?arnumber=11141737","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T18:39:23Z","timestamp":1764873563000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11141737\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":94,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2025.3602796","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}