{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T17:02:42Z","timestamp":1785603762229,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["NSF-IIS 1747614, NSF-IIS 2141037"],"award-info":[{"award-number":["NSF-IIS 1747614, NSF-IIS 2141037"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671897","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:55:12Z","timestamp":1724561712000},"page":"3345-3355","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":63,"title":["FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0541-1901","authenticated-orcid":false,"given":"Feijie","family":"Wu","sequence":"first","affiliation":[{"name":"Purdue University, West Lafayette, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5461-6693","authenticated-orcid":false,"given":"Zitao","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, Bellevue, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4204-6096","authenticated-orcid":false,"given":"Yaliang","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group, Bellevue, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1535-9692","authenticated-orcid":false,"given":"Bolin","family":"Ding","sequence":"additional","affiliation":[{"name":"Alibaba Group, Bellevue, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1557-7553","authenticated-orcid":false,"given":"Jing","family":"Gao","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proc. of International Conference on Learning Representations (ICLR'20)","author":"Emre Acar Durmus Alp","year":"2020","unstructured":"Durmus Alp Emre Acar, Yue Zhao, Ramon Matas, Matthew Mattina, Paul Whatmough, and Venkatesh Saligrama. 2020. Federated Learning Based on Dynamic Regularization. In Proc. of International Conference on Learning Representations (ICLR'20)."},{"key":"e_1_3_2_2_2_1","unstructured":"CCPA. 2023. California Consumer Privacy Act (CCPA). https:\/\/oag.ca.gov\/privacy\/ccpa"},{"key":"e_1_3_2_2_3_1","volume-title":"Code Alpaca: An Instruction-following LLaMA model for code generation. https:\/\/github.com\/sahil280114\/codealpaca.","author":"Chaudhary Sahil","year":"2023","unstructured":"Sahil Chaudhary. 2023. Code Alpaca: An Instruction-following LLaMA model for code generation. https:\/\/github.com\/sahil280114\/codealpaca."},{"key":"e_1_3_2_2_4_1","volume-title":"Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al.","author":"Chen Mark","year":"2021","unstructured":"Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, et al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021)."},{"key":"e_1_3_2_2_5_1","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano et al. 2021. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168 (2021)."},{"key":"e_1_3_2_2_6_1","volume-title":"Free Dolly: Introducing the World's First Truly Open Instruction-Tuned LLM. https:\/\/www.databricks.com\/blog\/2023\/04\/12\/dolly-first-open-commercially-viable-instruction-tuned-llm","author":"Conover Mike","year":"2023","unstructured":"Mike Conover, Matt Hayes, Ankit Mathur, Jianwei Xie, Jun Wan, Sam Shah, Ali Ghodsi, Patrick Wendell, Matei Zaharia, and Reynold Xin. 2023. Free Dolly: Introducing the World's First Truly Open Instruction-Tuned LLM. https:\/\/www.databricks.com\/blog\/2023\/04\/12\/dolly-first-open-commercially-viable-instruction-tuned-llm"},{"key":"e_1_3_2_2_7_1","volume-title":"Chatlaw: Open-source legal large language model with integrated external knowledge bases. arXiv preprint arXiv:2306.16092","author":"Cui Jiaxi","year":"2023","unstructured":"Jiaxi Cui, Zongjian Li, Yang Yan, Bohua Chen, and Li Yuan. 2023. Chatlaw: Open-source legal large language model with integrated external knowledge bases. arXiv preprint arXiv:2306.16092 (2023)."},{"key":"e_1_3_2_2_8_1","unstructured":"GDPR. 2016. Regulation (EU) 2016\/679 of the European Parliament and of the Council. https:\/\/data.europa.eu\/eli\/reg\/2016\/679\/oj"},{"key":"e_1_3_2_2_9_1","volume-title":"Proc. of Machine Learning and Systems (MLSys'23)","author":"He Shiqi","year":"2023","unstructured":"Shiqi He, Qifan Yan, Feijie Wu, Lanjun Wang, Mathias L\u00e9cuyer, and Ivan Beschastnikh. 2023. GlueFL: Reconciling Client Sampling and Model Masking for Bandwidth Efficient Federated Learning. Proc. of Machine Learning and Systems (MLSys'23)."},{"key":"e_1_3_2_2_10_1","volume-title":"Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531","author":"Hinton Geoffrey","year":"2015","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 (2015)."},{"key":"e_1_3_2_2_11_1","volume-title":"Proc. of International Conference on Learning Representations (ICLR'21)","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2021. LoRA: Low-Rank Adaptation of Large Language Models. In Proc. of International Conference on Learning Representations (ICLR'21)."},{"key":"e_1_3_2_2_12_1","volume-title":"Proc. of International conference on machine learning (ICML'20)","author":"Karimireddy Sai Praneeth","year":"2020","unstructured":"Sai Praneeth Karimireddy, Satyen Kale, Mehryar Mohri, Sashank Reddi, Sebastian Stich, and Ananda Theertha Suresh. 2020. Scaffold: Stochastic controlled averaging for federated learning. In Proc. of International conference on machine learning (ICML'20). 5132--5143."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671573"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_3_2_2_15_1","volume-title":"Proc. of International Conference on Learning Representations (ICLR'19)","author":"Li Xiang","year":"2019","unstructured":"Xiang Li, Kaixuan Huang, Wenhao Yang, Shusen Wang, and Zhihua Zhang. 2019. On the Convergence of FedAvg on Non-IID Data. In Proc. of International Conference on Learning Representations (ICLR'19)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"e_1_3_2_2_17_1","unstructured":"Percy Liang Rishi Bommasani Tony Lee Dimitris Tsipras Dilara Soylu Michihiro Yasunaga Yian Zhang Deepak Narayanan Yuhuai Wu Ananya Kumar et al. 2022. Holistic evaluation of language models. arXiv preprint arXiv:2211.09110 (2022)."},{"key":"e_1_3_2_2_18_1","volume-title":"Proc. of Advances in Neural Information Processing Systems (NeurIPS'20)","author":"Lin Tao","year":"2020","unstructured":"Tao Lin, Lingjing Kong, Sebastian U Stich, and Martin Jaggi. 2020. Ensemble distillation for robust model fusion in federated learning. In Proc. of Advances in Neural Information Processing Systems (NeurIPS'20). 2351--2363."},{"key":"e_1_3_2_2_19_1","volume-title":"Efficient federated prompt tuning for black-box large pre-trained models. arXiv preprint arXiv:2310.03123","author":"Lin Zihao","year":"2023","unstructured":"Zihao Lin, Yan Sun, Yifan Shi, Xueqian Wang, Lifu Huang, Li Shen, and Dacheng Tao. 2023. Efficient federated prompt tuning for black-box large pre-trained models. arXiv preprint arXiv:2310.03123 (2023)."},{"key":"e_1_3_2_2_20_1","volume-title":"GPT understands, too. AI Open","author":"Liu Xiao","year":"2023","unstructured":"Xiao Liu, Yanan Zheng, Zhengxiao Du, Ming Ding, Yujie Qian, Zhilin Yang, and Jie Tang. 2023. GPT understands, too. AI Open (2023)."},{"key":"e_1_3_2_2_21_1","volume-title":"Proc. of International Conference on Learning Representations (ICLR'18)","author":"Loshchilov Ilya","year":"2018","unstructured":"Ilya Loshchilov and Frank Hutter. 2018. Decoupled Weight Decay Regularization. In Proc. of International Conference on Learning Representations (ICLR'18)."},{"key":"e_1_3_2_2_22_1","volume-title":"Proc. of Artificial intelligence and statistics (AISTAT'17)","author":"McMahan Brendan","year":"2017","unstructured":"Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas. 2017. Communication-efficient learning of deep networks from decentralized data. In Proc. of Artificial intelligence and statistics (AISTAT'17). 1273--1282."},{"key":"e_1_3_2_2_23_1","article-title":"Large language models as tax attorneys: a case study in legal capabilities emergence","volume":"382","author":"Nay John J","year":"2024","unstructured":"John J Nay, David Karamardian, Sarah B Lawsky, Wenting Tao, Meghana Bhat, Raghav Jain, Aaron Travis Lee, Jonathan H Choi, and Jungo Kasai. 2024. Large language models as tax attorneys: a case study in legal capabilities emergence. Philosophical Transactions of the Royal Society A, Vol. 382, 2270 (2024), 20230159.","journal-title":"Philosophical Transactions of the Royal Society A"},{"key":"e_1_3_2_2_24_1","unstructured":"OpenAI. 2023. Fine-tuning - OpenAI API. https:\/\/platform.openai.com\/docs\/guides\/fine-tuning. Accessed: 2023-09--29."},{"key":"e_1_3_2_2_25_1","volume-title":"Proc. of Advances in Neural Information Processing Systems (NeurIPS'22)","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. In Proc. of Advances in Neural Information Processing Systems (NeurIPS'22). 27730--27744."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101429"},{"key":"e_1_3_2_2_27_1","volume-title":"Nathan Scales, Ajay Tanwani, Heather Cole-Lewis, Stephen Pfohl, et al.","author":"Singhal Karan","year":"2023","unstructured":"Karan Singhal, Shekoofeh Azizi, Tao Tu, S Sara Mahdavi, Jason Wei, Hyung Won Chung, Nathan Scales, Ajay Tanwani, Heather Cole-Lewis, Stephen Pfohl, et al. 2023. Large language models encode clinical knowledge. Nature, Vol. 620, 7972 (2023), 172--180."},{"key":"e_1_3_2_2_28_1","volume-title":"Proc. of Advances in Neural Information Processing Systems (NeurIPS'23)","author":"Sordoni Alessandro","year":"2023","unstructured":"Alessandro Sordoni, Xingdi Yuan, Marc-Alexandre C\u00f4t\u00e9, Matheus Pereira, Adam Trischler, Ziang Xiao, Arian Hosseini, Friederike Niedtner, and Nicolas Le Roux. 2023. Joint prompt optimization of stacked llms using variational inference. In Proc. of Advances in Neural Information Processing Systems (NeurIPS'23)."},{"key":"e_1_3_2_2_29_1","volume-title":"FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models. arXiv preprint arXiv:2310.01467","author":"Sun Jingwei","year":"2023","unstructured":"Jingwei Sun, Ziyue Xu, Hongxu Yin, Dong Yang, Daguang Xu, Yiran Chen, and Holger R Roth. 2023. FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Models. arXiv preprint arXiv:2310.01467 (2023)."},{"key":"e_1_3_2_2_30_1","volume-title":"Proc. of The International Conference on Learning Representations (ICLR'24)","author":"Sun Youbang","year":"2024","unstructured":"Youbang Sun, Zitao Li, Yaliang Li, and Bolin Ding. 2024. Improving LoRA in Privacy-preserving Federated Learning. In Proc. of The International Conference on Learning Representations (ICLR'24)."},{"key":"e_1_3_2_2_31_1","volume-title":"Hashimoto","author":"Taori Rohan","year":"2023","unstructured":"Rohan Taori, Ishaan Gulrajani, Tianyi Zhang, Yann Dubois, Xuechen Li, Carlos Guestrin, Percy Liang, and Tatsunori B. Hashimoto. 2023. Stanford Alpaca: An Instruction-following LLaMA model. https:\/\/github.com\/tatsu-lab\/stanford_alpaca."},{"key":"e_1_3_2_2_32_1","volume-title":"Kabilan Elangovan, Laura Gutierrez, Ting Fang Tan, and Daniel Shu Wei Ting.","author":"Thirunavukarasu Arun James","year":"2023","unstructured":"Arun James Thirunavukarasu, Darren Shu Jeng Ting, Kabilan Elangovan, Laura Gutierrez, Ting Fang Tan, and Daniel Shu Wei Ting. 2023. Large language models in medicine. Nature medicine, Vol. 29, 8 (2023), 1930--1940."},{"key":"e_1_3_2_2_33_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_2_34_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01955"},{"key":"e_1_3_2_2_36_1","volume-title":"Proc. of The International Conference on Learning Representations (ICLR'23)","author":"Wang Haozhao","year":"2023","unstructured":"Haozhao Wang, Haoran Xu, Yichen Li, Yuan Xu, Ruixuan Li, and Tianwei Zhang. 2023. FedCDA: Federated Learning with Cross-rounds Divergence-aware Aggregation. In Proc. of The International Conference on Learning Representations (ICLR'23)."},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511988"},{"key":"e_1_3_2_2_38_1","volume-title":"Proc. of Advances in neural information processing systems (NeurIPS'20)","author":"Wang Jianyu","year":"2020","unstructured":"Jianyu Wang, Qinghua Liu, Hao Liang, Gauri Joshi, and H Vincent Poor. 2020. Tackling the objective inconsistency problem in heterogeneous federated optimization. In Proc. of Advances in neural information processing systems (NeurIPS'20). 7611--7623."},{"key":"e_1_3_2_2_39_1","volume-title":"Chatcad: Interactive computer-aided diagnosis on medical image using large language models. arXiv preprint arXiv:2302.07257","author":"Wang Sheng","year":"2023","unstructured":"Sheng Wang, Zihao Zhao, Xi Ouyang, Qian Wang, and Dinggang Shen. 2023. Chatcad: Interactive computer-aided diagnosis on medical image using large language models. arXiv preprint arXiv:2302.07257 (2023)."},{"key":"e_1_3_2_2_40_1","volume-title":"Proc. of International Conference on Learning Representations (ICLR'21)","author":"Wei Jason","year":"2021","unstructured":"Jason Wei, Maarten Bosma, Vincent Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le. 2021. Finetuned Language Models are Zero-Shot Learners. In Proc. of International Conference on Learning Representations (ICLR'21)."},{"key":"e_1_3_2_2_41_1","volume-title":"Proc. of Advances in Neural Information Processing Systems (NeurIPS'22)","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. In Proc. of Advances in Neural Information Processing Systems (NeurIPS'22). 24824--24837."},{"key":"e_1_3_2_2_42_1","volume-title":"Proc. of International Conference on Machine Learning (ICML'23)","author":"Wu Feijie","year":"2023","unstructured":"Feijie Wu, Song Guo, Zhihao Qu, Shiqi He, Ziming Liu, and Jing Gao. 2023. Anchor sampling for federated learning with partial client participation. In Proc. of International Conference on Machine Learning (ICML'23). 37379--37416."},{"key":"e_1_3_2_2_43_1","volume-title":"Offsite-tuning: Transfer learning without full model. arXiv preprint arXiv:2302.04870","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao, Ji Lin, and Song Han. 2023. Offsite-tuning: Transfer learning without full model. arXiv preprint arXiv:2302.04870 (2023)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.14778\/3579075.3579081"},{"key":"e_1_3_2_2_45_1","volume-title":"Fedlora: Model-heterogeneous personalized federated learning with lora tuning. arXiv preprint arXiv:2310.13283","author":"Yi Liping","year":"2023","unstructured":"Liping Yi, Han Yu, Gang Wang, and Xiaoguang Liu. 2023. Fedlora: Model-heterogeneous personalized federated learning with lora tuning. arXiv preprint arXiv:2310.13283 (2023)."},{"key":"e_1_3_2_2_46_1","volume-title":"Proc. of Advances in neural information processing systems (NeurIPS'14)","author":"Yosinski Jason","year":"2014","unstructured":"Jason Yosinski, Jeff Clune, Yoshua Bengio, and Hod Lipson. 2014. How transferable are features in deep neural networks?. In Proc. of Advances in neural information processing systems (NeurIPS'14)."},{"key":"e_1_3_2_2_47_1","volume-title":"Proc. of Advances in Neural Information Processing Systems (NeurIPS'21)","author":"Zhang Jie","year":"2021","unstructured":"Jie Zhang, Song Guo, Xiaosong Ma, Haozhao Wang, Wenchao Xu, and Feijie Wu. 2021. Parameterized knowledge transfer for personalized federated learning. In Proc. of Advances in Neural Information Processing Systems (NeurIPS'21). 10092--10104."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447454"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.632"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599790"}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671897","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671897","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:15Z","timestamp":1750291455000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671897"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":50,"alternative-id":["10.1145\/3637528.3671897","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671897","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}