{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T12:40:50Z","timestamp":1769863250041,"version":"3.49.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Longgang District Shenzhen","award":["LGKCSDPT 2024004"],"award-info":[{"award-number":["LGKCSDPT 2024004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1109\/tpds.2026.3654957","type":"journal-article","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T20:51:30Z","timestamp":1768596690000},"page":"680-696","source":"Crossref","is-referenced-by-count":0,"title":["Resource-Efficient Personal Large Language Models Fine-Tuning With Collaborative Edge Computing"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8867-0655","authenticated-orcid":false,"given":"Shengyuan","family":"Ye","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4408-2832","authenticated-orcid":false,"given":"Bei","family":"Ouyang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2802-2258","authenticated-orcid":false,"given":"Tianyi","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4800-8768","authenticated-orcid":false,"given":"Liekang","family":"Zeng","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4978-8607","authenticated-orcid":false,"given":"Jingyi","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4707-9492","authenticated-orcid":false,"given":"Jiangsu","family":"Du","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9745-4372","authenticated-orcid":false,"given":"Xiaowen","family":"Chu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1772-7751","authenticated-orcid":false,"given":"Guoliang","family":"Xing","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9943-6020","authenticated-orcid":false,"given":"Xu","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"140","key":"ref2","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1525\/9780520940420-020"},{"key":"ref4","article-title":"Personal LLM agents: Insights and survey about the capability, efficiency and security","author":"Li","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575698"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3513457"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM52122.2024.10621342"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3570361.3592505"},{"key":"ref9","article-title":"FlexLLM: A system for co-serving large language model inference and parameter-efficient finetuning","author":"Miao","year":"2024"},{"key":"ref10","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"key":"ref11","article-title":"LORA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2021"},{"key":"ref12","article-title":"Jetson-nano","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3495243.3560545"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3539765"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3498361.3538928"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_41"},{"key":"ref17","article-title":"Parameter-efficient fine-tuning for large models: A comprehensive survey","volume":"2024","author":"Han","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref18","first-page":"12991","article-title":"LST: Ladder side-tuning for parameter and memory efficient transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Sung","year":"2022"},{"key":"ref19","first-page":"17573","article-title":"POET: Training neural networks on tiny devices with integrated rematerialization and paging","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Patil","year":"2022"},{"key":"ref20","first-page":"22941","article-title":"On-device training under 256KB memory","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Lin","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-023-3131-8"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546617"},{"key":"ref24","first-page":"579","article-title":"FwdLLM: Efficient federated finetuning of large language models with perturbed inferences","volume-title":"Proc. USENIX Annu. Tech. Conf. (USENIX ATC 24)","author":"Xu","year":"2024"},{"key":"ref25","first-page":"1683","article-title":"Pruning filters for efficient convnets","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Li"},{"key":"ref26","first-page":"21702","article-title":"LLM-pruner: On the structural pruning of large language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Ma","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01544"},{"key":"ref28","article-title":"Torch-pruning: A structured pruning toolkit for pytorch","volume-title":"GitHub Repository","year":"2023"},{"key":"ref29","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref30","first-page":"13\u2009278","article-title":"MiniLLM: Knowledge distillation of large language models","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Gu","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01065"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.507"},{"key":"ref33","article-title":"Distilling step-by-step","author":"Research","year":"2021"},{"key":"ref34","first-page":"30318","article-title":"GPT3.int8(): 8-bit matrix multiplication for transformers at scale","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Dettmers","year":"2022"},{"key":"ref35","first-page":"10088","article-title":"QLoRA: Efficient finetuning of quantized LLMs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Dettmers","year":"2024"},{"key":"ref36","first-page":"7750","article-title":"The case for 4-bit precision: K-bit inference scaling laws","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dettmers","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3453142.3491286"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3545008.3545015"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359646"},{"key":"ref41","article-title":"Pytorch","year":"2019"},{"key":"ref42","first-page":"1","article-title":"MNN: A universal and efficient inference engine","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Jiang","year":"2020"},{"key":"ref43","article-title":"On-device training with tensorflow lite","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3649361"},{"key":"ref45","article-title":"Jetson-tx2","year":"2017"},{"key":"ref46","first-page":"19","article-title":"Communication efficient distributed machine learning with the parameter server","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Li","year":"2014"},{"key":"ref47","first-page":"103","article-title":"GPipe: Efficient training of giant neural networks using pipeline parallelism","volume-title":"Proc. NeurIPS","volume":"32","author":"Huang","year":"2019"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3636534.3649363"},{"key":"ref49","first-page":"307","article-title":"$\\lbrace${HetPipe $\\rbrace$}: Enabling large $\\lbrace${ DNN$\\rbrace$} training on (whimpy) heterogeneous $\\lbrace${GPU$\\rbrace$} clusters through integration of pipelined model parallelism and data parallelism","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Park","year":"2020"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3673038.3673043"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680940"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.004.2300479"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/11368703\/11355763.pdf?arnumber=11355763","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T21:05:18Z","timestamp":1769807118000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11355763\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":52,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2026.3654957","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]}}}