{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:44:34Z","timestamp":1782798274294,"version":"3.54.5"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T00:00:00Z","timestamp":1779062400000},"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":[],"published-print":{"date-parts":[[2026,5,18]]},"DOI":"10.1109\/infocom59046.2026.11571394","type":"proceedings-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:38:15Z","timestamp":1782761895000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["ZorBA: Zeroth-order Federated Fine-tuning of LLMs with Heterogeneous Block Activation"],"prefix":"10.1109","author":[{"given":"Chuiyang","family":"Meng","sequence":"first","affiliation":[{"name":"The University of British Columbia,Department of Electrical and Computer Engineering,Vancouver,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Tang","sequence":"additional","affiliation":[{"name":"Southern University of Science and Technology,Department of Computer Science and Engineering,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vincent W.S.","family":"Wong","sequence":"additional","affiliation":[{"name":"The University of British Columbia,Department of Electrical and Computer Engineering,Vancouver,Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-026-60308-3"},{"key":"ref2","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref3","article-title":"The Llama 3 herd of models","author":"Grattafiori","year":"2024"},{"key":"ref4","article-title":"Gemma 2: Improving open language models at a practical size","author":"Team","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044734"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"ref7","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Hu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0142"},{"key":"ref9","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist. (AISTATS)","author":"McMahan"},{"key":"ref10","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst. (MLSys)","author":"Li"},{"key":"ref11","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Karimireddy"},{"key":"ref12","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","author":"Wang","year":"2020","journal-title":"Advances Neural Info. Process. Syst. (NeurIPS)"},{"key":"ref13","article-title":"Federated full-parameter tuning of billion-sized language models with communication cost under 18 kilobytes","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Qin"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447454"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0708"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0461"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2025.3531128"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM55648.2025.11044514"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2207"},{"key":"ref20","article-title":"Zeroth-order optimization with trajectory-informed derivative estimation","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Shu"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2308"},{"key":"ref22","article-title":"DeepZero: Scaling up zeroth-order optimization for deep model training","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Chen"},{"key":"ref23","article-title":"Revisiting zeroth-order optimization for memory-efficient LLM fine-tuning: A benchmark","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Zhang"},{"key":"ref24","article-title":"Revisiting zeroth-order optimization: Minimum-variance two-point estimators and directionally aligned perturbations","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Ma"},{"key":"ref25","article-title":"Enhancing zeroth-order fine-tuning for language models with low-rank structures","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Chen"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3214122"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2374"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0151"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671865"},{"key":"ref30","article-title":"Achieving dimension-free communication in federated learning via zeroth-order optimization","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Li"},{"key":"ref31","article-title":"Ferret: Federated full-parameter tuning at scale for large language models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Shu"},{"key":"ref32","article-title":"On the convergence of FedAvg on non-IID data","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Li"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3562834"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1971.4308298"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1007\/11685654_10","article-title":"Dinitz\u2019algorithm: The original version and even\u2019s version","volume-title":"Theoretical Computer Science: Essays in Memory of Shimon Even","author":"Dinitz","year":"2006"},{"key":"ref37","volume-title":"Linear and Nonlinear Optimization","author":"Griva","year":"2008"},{"key":"ref38","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref39","volume-title":"AG\u2019s corpus of news articles","author":"Gulli"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1075"}],"event":{"name":"IEEE INFOCOM 2026 - IEEE Conference on Computer Communications","location":"Tokyo, Japan","start":{"date-parts":[[2026,5,18]]},"end":{"date-parts":[[2026,5,21]]}},"container-title":["IEEE INFOCOM 2026 - IEEE Conference on Computer Communications"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11571071\/11571169\/11571394.pdf?arnumber=11571394","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T05:12:33Z","timestamp":1782796353000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11571394\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,18]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/infocom59046.2026.11571394","relation":{},"subject":[],"published":{"date-parts":[[2026,5,18]]}}}