{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T12:27:46Z","timestamp":1770812866789,"version":"3.50.1"},"reference-count":59,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Signal Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tsp.2026.3652487","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:04:28Z","timestamp":1768255468000},"page":"293-308","source":"Crossref","is-referenced-by-count":0,"title":["A Multi-Token Coordinate Descent Method for Semi-Decentralized Vertical Federated Learning"],"prefix":"10.1109","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2677-8710","authenticated-orcid":false,"given":"Pedro","family":"Valdeira","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213 USA, also with the Instituto Superior T\u00e9cnico, Universidade de Lisboa, 1049-001 Lisbon, Portugal, and also with the Laboratory for Robotics and Engineering Systems, Institute for Systems and Robotics, Lisbon, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6766-5459","authenticated-orcid":false,"given":"Yuejie","family":"Chi","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3071-6627","authenticated-orcid":false,"given":"Cl\u00e1udia","family":"Soares","sequence":"additional","affiliation":[{"name":"Computer Science Department, Universidade Nova de Lisboa Faculdade de Ciencias e Tecnologia, Caparica, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9669-8532","authenticated-orcid":false,"given":"Jo\u00e3o","family":"Xavier","sequence":"additional","affiliation":[{"name":"Instituto Superior T\u00e9cnico, Universidade de Lisboa, 1049-001 Lisbon, Portugal, and also with the Laboratory for Robotics and Engineering Systems, Institute for Systems and Robotics, Lisbon, Portugal"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A multi-token coordinate descent method for vertical\n                        federated learning","volume-title":"Proc. NeurIPS\n                        Workshop Federated Learn.: Recent Adv. New Challenges","author":"Valdeira","year":"2022"},{"key":"ref2","first-page":"1273","article-title":"Communication-efficient learning of deep networks\n                        from decentralized data","volume-title":"Proc. Artif.\n                        Intell. Statist.","author":"McMahan","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3352628"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3387107"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10091012"},{"key":"ref6","article-title":"Can decentralized algorithms outperform centralized\n                        algorithms? A case study for decentralized parallel stochastic gradient\n                        descent","volume":"30","author":"Lian","year":"2017","journal-title":"Proc. Adv. Neural Inf. Process.\n                        Syst."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.2009515"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2011.2161027"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2254478"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2017.2698261"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSIPN.2017.2695121"},{"key":"ref12","first-page":"5381","article-title":"A unified theory of decentralized SGD with changing\n                        topology and local updates","volume-title":"Proc. Int.\n                        Conf. Mach. Learn.,","author":"Koloskova","year":"2020"},{"issue":"1","key":"ref13","article-title":"Communication-efficient distributed optimization in\n                        networks with gradient tracking and variance\n                    reduction","volume":"21","author":"Li","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref14","first-page":"31\u2009653","article-title":"BEER: Fast O(1\/t) rate for decentralized nonconvex\n                        optimization with communication compression","volume-title":"Proc. Adv. Neural Information Process. Syst.","volume":"35","author":"Zhao","year":"2022"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2817461"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/S1052623495287022"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1137\/S1052623499362111"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1137\/080726380"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1137\/08073038X"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2020.2983167"},{"key":"ref21","first-page":"470","article-title":"A principled framework for the design and analysis of\n                        token algorithms","volume-title":"Proc. Int. Conf. Artif.\n                        Intell. Statist.,","author":"Hendrikx","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2019.2955442"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2022.3230335"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1378533.1378557"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3118344"},{"issue":"230","key":"ref26","first-page":"1","article-title":"CoCoA: A general framework for\n                        communication-efficient distributed optimization","volume":"18","author":"Smith","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref27","article-title":"COLA: Decentralized linear\n                    learning","volume":"31","author":"He","year":"2018","journal-title":"Proc. Adv. Neural Inf. Process.\n                        Syst."},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3114978"},{"key":"ref29","article-title":"VAFL: A method of vertical asynchronous federated\n                        learning","author":"Chen","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3198176"},{"key":"ref31","first-page":"2738","article-title":"Compressed-VFL: Communication-efficient learning with\n                        vertically partitioned data","volume-title":"Proc. Int.\n                        Conf. Mach. Learn.","author":"Castiglia","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2025.3540655"},{"key":"ref33","article-title":"\u201cFault tolerant serverless VFL over dynamic device\n                        environment,\u201d","author":"Ganguli","year":"2024"},{"key":"ref34","article-title":"Vertical federated learning with missing features\n                        during training and inference","volume-title":"Proc. 13th\n                        Int. Conf. Learn. Representations","author":"Valdeira","year":"2025"},{"key":"ref35","article-title":"Hybrid federated learning: Algorithms and\n                        implementation","author":"Zhang","year":"2020"},{"key":"ref36","article-title":"A survey on vertical\n                        federated learning: From a layered perspective","author":"Yang","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-015-0892-3"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1137\/120887679"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1137\/100802001"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-012-0614-z"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10589-019-00140-7"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1137\/130949993"},{"key":"ref43","article-title":"Hybrid local SGD for federated learning with\n                        heterogeneous communications","volume-title":"Proc. Int.\n                        Conf. Learn. Representations","author":"Guo","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TSIPN.2025.3539004"},{"key":"ref45","article-title":"Mobility improves the convergence of asynchronous\n                        federated learning","author":"Bian","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3342095"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC49053.2021.9417459"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3143495"},{"key":"ref49","article-title":"SplitNN-driven vertical\n                        partitioning","author":"Ceballos","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/1366919.1366929"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-12-604550-5.50015-8"},{"issue":"83","key":"ref52","first-page":"1","article-title":"CVXPY: A Python-embedded modeling language for convex\n                        optimization","volume":"17","author":"Diamond","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref53","article-title":"Result analysis of the NIPS 2003 feature selection\n                        challenge","volume":"17","author":"Guyon","year":"2004","journal-title":"Proc. Adv. Neural Inf.\n                        Process. Syst."},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref57","article-title":"Learning multiple layers of features from tiny\n                        images","author":"Krizhevsky"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/0041-5553(63)90382-3"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1214\/EJP.v20-4039"}],"container-title":["IEEE Transactions on Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/78\/11345506\/11346542.pdf?arnumber=11346542","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T05:55:33Z","timestamp":1770789333000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11346542\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tsp.2026.3652487","relation":{},"ISSN":["1053-587X","1941-0476"],"issn-type":[{"value":"1053-587X","type":"print"},{"value":"1941-0476","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}