{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:10:57Z","timestamp":1784736657468,"version":"3.55.0"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["25ZR1401016"],"award-info":[{"award-number":["25ZR1401016"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Hong Kong Jockey Club Charities Trust"},{"name":"Hong Kong SAR Government"},{"name":"Research Grants Council of Hong Kong","award":["27213824"],"award-info":[{"award-number":["27213824"]}]},{"name":"CRS","award":["HKU702\/24"],"award-info":[{"award-number":["HKU702\/24"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tmc.2025.3649881","type":"journal-article","created":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T18:46:20Z","timestamp":1767206780000},"page":"8782-8797","source":"Crossref","is-referenced-by-count":11,"title":["Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Models"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0844-9879","authenticated-orcid":false,"given":"Zihan","family":"Fang","sequence":"first","affiliation":[{"name":"Institute of Space Internet, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4463-5652","authenticated-orcid":false,"given":"Zheng","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3215-2696","authenticated-orcid":false,"given":"Zhe","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Space Internet, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4295-940X","authenticated-orcid":false,"given":"Xianhao","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6502-9910","authenticated-orcid":false,"given":"Yue","family":"Gao","sequence":"additional","affiliation":[{"name":"Institute of Space Internet, Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1079-3871","authenticated-orcid":false,"given":"Yuguang","family":"Fang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"8","key":"ref1","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref3","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"issue":"240","key":"ref4","first-page":"1","article-title":"PaLM: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","article-title":"FDAPT: Federated domain-adaptive pre-training for language models","author":"Jiang","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3659604"},{"key":"ref7","first-page":"25464","article-title":"Decentralized training of foundation models in heterogeneous environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yuan","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00652-2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538917"},{"key":"ref10","first-page":"18712","article-title":"Flow: Per-instance personalized federated learning","volume-title":"Proc. 37th NeurIPS","author":"Panchal","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CCNC51644.2023.10060782"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN54338.2022.00029"},{"key":"ref13","article-title":"FedGP: Buffer-based gradient projection for continual federated learning","volume-title":"Proc. 6th MLSys","author":"Dai","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISCC58397.2023.10217850"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3613277"},{"key":"ref16","article-title":"Confidant: Customizing transformer-based LLMs via collaborative edge training","author":"Chen","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3581791.3596844"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/455"},{"key":"ref19","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"ref21","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref22","first-page":"1022","article-title":"Compacter: Efficient low-rank hypercomplex adapter layers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mahabadi","year":"2021"},{"key":"ref23","first-page":"24193","article-title":"Training neural networks with fixed sparse masks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sung","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00164"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.319"},{"key":"ref26","article-title":"S-LoRA: Serving thousands of concurrent LoRA adapters","author":"Sheng","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592505"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-40292-0_1"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.488"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2022.3205475"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.2994391"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00535"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3554980"},{"key":"ref35","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","author":"McMahan","year":"2017"},{"key":"ref36","article-title":"CaraServe: CPU-assisted and rank-aware LoRA serving for generative LLM inference","author":"Li","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.568"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3603287.3651205"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3513457"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2025.3527641"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1201\/9781003010623-15"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"ref43","first-page":"26809","article-title":"PLATON: Pruning large transformer models with upper confidence bound of weight importance","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Zhang","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.510"},{"key":"ref45","article-title":"8-Bit optimizers via block-wise quantization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dettmers","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref47","article-title":"Stanford alpaca: An instruction-following llama model","author":"Taori","year":"2023"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5525"},{"key":"ref49","article-title":"Selective aggregation for low-rank adaptation in federated learning","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Guo","year":"2025"},{"key":"ref50","article-title":"Federated residual low-rank adaptation of large language models","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Yan","year":"2025"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.13"},{"key":"ref52","first-page":"1223","article-title":"More effective distributed ML via a stale synchronous parallel parameter server","volume-title":"Proc. 27th Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2013"},{"key":"ref53","article-title":"To prune, or not to prune: Exploring the efficacy of pruning for model compression","author":"Zhu","year":"2017"},{"key":"ref54","first-page":"20378","article-title":"Movement pruning: Adaptive sparsity by fine-tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Sanh","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3510418"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.008.2300516"},{"key":"ref57","first-page":"41473","article-title":"Federated full-parameter tuning of billion-sized language models with communication cost under 18 kilobytes","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"235","author":"Qin","year":"2024"},{"key":"ref58","article-title":"FWDLLM: Efficient FEDLLM using forward gradient","author":"Xu","year":"2023"},{"key":"ref59","first-page":"560","article-title":"signSGD: Compressed optimisation for non-convex problems","volume-title":"Proc. 35th Int. Conf. Meach. Learn.","author":"Bernstein","year":"2018"},{"key":"ref60","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Frantar","year":"2023"},{"key":"ref61","first-page":"87","article-title":"AWQ: Activation-aware weight quantization for LLM compression and acceleration","volume-title":"Proc. MLSys","volume":"6","author":"Lin","year":"2024"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0451"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488906"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737464"},{"key":"ref65","first-page":"9329","article-title":"Wide compression: Tensor ring nets","volume-title":"Proc. IEEE\/CVF Conf. Conf. Vis. Pattern. Recognit.","author":"Wang","year":"2018"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3517017"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3397677"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3481275"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7755\/11511860\/11320816.pdf?arnumber=11320816","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T05:06:25Z","timestamp":1778216785000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11320816\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":68,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tmc.2025.3649881","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.173272996.63900291\/v1","asserted-by":"object"}]},"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":[[2026,6]]}}}