{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T16:57:29Z","timestamp":1791910649772,"version":"4.3.4"},"publisher-location":"New York, NY, USA","reference-count":65,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671865","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T00:55:12Z","timestamp":1724547312000},"page":"1827-1838","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["On the Convergence of Zeroth-Order Federated Tuning for Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7834-8444","authenticated-orcid":false,"given":"Zhenqing","family":"Ling","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8015-2121","authenticated-orcid":false,"given":"Daoyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3828-796X","authenticated-orcid":false,"given":"Liuyi","family":"Yao","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, Zhejiang, China"}],"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, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3220-904X","authenticated-orcid":false,"given":"Ying","family":"Shen","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University &amp; Pazhou Lab, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Extended version of this paper. arXiv preprint arXiv:2402.05926."},{"key":"e_1_3_2_2_2_1","volume-title":"Information-theoretic lower bounds on the oracle complexity of convex optimization. Advances in Neural Information Processing Systems 22","author":"Agarwal Alekh","year":"2009","unstructured":"Alekh Agarwal, Martin J Wainwright, Peter Bartlett, and Pradeep Ravikumar. 2009. Information-theoretic lower bounds on the oracle complexity of convex optimization. Advances in Neural Information Processing Systems 22 (2009)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.568"},{"key":"e_1_3_2_2_4_1","volume-title":"Federated Fine-tuning of Large Language Models under Heterogeneous Language Tasks and Client Resources. arXiv preprint arXiv:2402.11505","author":"Bai Jiamu","year":"2024","unstructured":"Jiamu Bai, Daoyuan Chen, Bingchen Qian, Liuyi Yao, and Yaliang Li. 2024. Federated Fine-tuning of Large Language Models under Heterogeneous Language Tasks and Client Resources. arXiv preprint arXiv:2402.11505 (2024)."},{"key":"e_1_3_2_2_5_1","series-title":"SIAM review 60, 2","volume-title":"Optimization methods for large-scale machine learning","author":"Bottou L\u00e9on","year":"2018","unstructured":"L\u00e9on Bottou, Frank E Curtis, and Jorge Nocedal. 2018. Optimization methods for large-scale machine learning. SIAM review 60, 2 (2018), 223--311."},{"key":"e_1_3_2_2_6_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems 33 (2020) 1877--1901."},{"key":"e_1_3_2_2_7_1","unstructured":"Sahil Chaudhary. 2023. Code alpaca: An instruction-following llama model for code generation."},{"key":"e_1_3_2_2_8_1","volume-title":"Federated large language model: A position paper. arXiv preprint arXiv:2307.08925","author":"Chen Chaochao","year":"2023","unstructured":"Chaochao Chen, Xiaohua Feng, Jun Zhou, Jianwei Yin, and Xiaolin Zheng. 2023. Federated large language model: A position paper. arXiv preprint arXiv:2307.08925 (2023)."},{"key":"e_1_3_2_2_9_1","unstructured":"Daoyuan Chen Dawei Gao Weirui Kuang Yaliang Li and Bolin Ding. 2022. pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learning. In NeurIPS."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599829"},{"key":"e_1_3_2_2_11_1","volume-title":"Data-Juicer: A One-Stop Data Processing System for Large Language Models. In International Conference on Management of Data.","author":"Chen Daoyuan","year":"2024","unstructured":"Daoyuan Chen, Yilun Huang, Zhijian Ma, Hesen Chen, Xuchen Pan, Ce Ge, Dawei Gao, Yuexiang Xie, Zhaoyang Liu, Jinyang Gao, Yaliang Li, Bolin Ding, and Jingren Zhou. 2024. Data-Juicer: A One-Stop Data Processing System for Large Language Models. In International Conference on Management of Data."},{"key":"e_1_3_2_2_12_1","volume-title":"International Conference on Machine Learning, ICML","volume":"202","author":"Chen Daoyuan","year":"2023","unstructured":"Daoyuan Chen, Liuyi Yao, Dawei Gao, Bolin Ding, and Yaliang Li. 2023. Efficient Personalized Federated Learning via Sparse Model-Adaptation. In International Conference on Machine Learning, ICML, Vol. 202. 5234--5256."},{"key":"e_1_3_2_2_13_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_14_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_15_1","unstructured":"Mike Conover Matt Hayes Ankit Mathur Xiangrui Meng Jianwei Xie Jun Wan Sam Shah Ali Ghodsi Patrick Wendell Matei Zaharia et al. 2023. Free dolly: Introducing the world's first truly open instruction-tuned llm."},{"key":"e_1_3_2_2_16_1","volume-title":"Free Dolly: Introducing the World's First Truly Open 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."},{"key":"e_1_3_2_2_17_1","volume-title":"Glm: General language model pretraining with autoregressive blank infilling. arXiv preprint arXiv:2103.10360","author":"Du Zhengxiao","year":"2021","unstructured":"Zhengxiao Du, Yujie Qian, Xiao Liu, Ming Ding, Jiezhong Qiu, Zhilin Yang, and Jie Tang. 2021. Glm: General language model pretraining with autoregressive blank infilling. arXiv preprint arXiv:2103.10360 (2021)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2015.2409256"},{"key":"e_1_3_2_2_19_1","volume-title":"NeurIPS","author":"Fallah Alireza","year":"2020","unstructured":"Alireza Fallah, Aryan Mokhtari, and Asuman Ozdaglar. 2020. Personalized federated learning: A meta-learning approach. In NeurIPS 2020."},{"key":"e_1_3_2_2_20_1","volume-title":"FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models. CoRR abs\/2310.10049","author":"Fan Tao","year":"2023","unstructured":"Tao Fan, Yan Kang, Guoqiang Ma, Weijing Chen, Wenbin Wei, Lixin Fan, and Qiang Yang. 2023. FATE-LLM: A Industrial Grade Federated Learning Framework for Large Language Models. CoRR abs\/2310.10049 (2023)."},{"key":"e_1_3_2_2_21_1","volume-title":"Fate-llm: A industrial grade federated learning framework for large language models. arXiv preprint arXiv:2310.10049","author":"Fan Tao","year":"2023","unstructured":"Tao Fan, Yan Kang, Guoqiang Ma, Weijing Chen, Wenbin Wei, Lixin Fan, and Qiang Yang. 2023. Fate-llm: A industrial grade federated learning framework for large language models. arXiv preprint arXiv:2310.10049 (2023)."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3214122"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-017-0621-6"},{"key":"e_1_3_2_2_24_1","volume-title":"International Conference on Machine Learning. PMLR, 2232--2241","author":"Ghorbani Behrooz","year":"2019","unstructured":"Behrooz Ghorbani, Shankar Krishnan, and Ying Xiao. 2019. An investigation into neural net optimization via hessian eigenvalue density. In International Conference on Machine Learning. PMLR, 2232--2241."},{"key":"e_1_3_2_2_25_1","volume-title":"Proceedings of the AAAI conference on artificial intelligence","volume":"35","author":"Gu Jiaqi","year":"2021","unstructured":"Jiaqi Gu, Chenghao Feng, Zheng Zhao, Zhoufeng Ying, Ray T Chen, and David Z Pan. 2021. Efficient on-chip learning for optical neural networks through poweraware sparse zeroth-order optimization. In Proceedings of the AAAI conference on artificial intelligence, Vol. 35. 7583--7591."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2896025"},{"key":"e_1_3_2_2_27_1","volume-title":"Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300","author":"Hendrycks Dan","year":"2020","unstructured":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2020. Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300 (2020)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","unstructured":"Junyuan Hong Zhuangdi Zhu Shuyang Yu Zhangyang Wang Hiroko Dodge and Jiayu Zhou. 2021. Federated Adversarial Debiasing for Fair and Transferable Representations. In KDD.","DOI":"10.1145\/3447548.3467281"},{"key":"e_1_3_2_2_29_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https: \/\/openreview.net\/forum?id=nZeVKeeFYf9","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, yelong shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https: \/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"e_1_3_2_2_30_1","volume-title":"Query complexity of derivative-free optimization. Advances in Neural Information Processing Systems 25","author":"Jamieson Kevin G","year":"2012","unstructured":"Kevin G Jamieson, Robert Nowak, and Ben Recht. 2012. Query complexity of derivative-free optimization. Advances in Neural Information Processing Systems 25 (2012)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Peter Kairouz H. Brendan McMahan Brendan Avent Aur\u00e9lien Bellet Mehdi Bennis Arjun Nitin Bhagoji Kallista Bonawitz Zachary Charles Graham Cormode Rachel Cummings Rafael G. L. D'Oliveira Hubert Eichner Salim El Rouayheb David Evans Josh Gardner Zachary Garrett Adri\u00e0 Gasc\u00f3n Badih Ghazi Phillip B. Gibbons Marco Gruteser Zaid Harchaoui Chaoyang He Lie He Zhouyuan Huo Ben Hutchinson Justin Hsu Martin Jaggi Tara Javidi Gauri Joshi Mikhail Khodak Jakub Konecn\u00fd Aleksandra Korolova Farinaz Koushanfar Sanmi Koyejo Tancr\u00e8de Lepoint Yang Liu Prateek Mittal Mehryar Mohri Richard Nock Ayfer \u00d6zg\u00fcr Rasmus Pagh Hang Qi Daniel Ramage Ramesh Raskar Mariana Raykova Dawn Song Weikang Song Sebastian U. Stich Ziteng Sun Ananda Theertha Suresh Florian Tram\u00e8r Praneeth Vepakomma Jianyu Wang Li Xiong Zheng Xu Qiang Yang Felix X. Yu Han Yu and Sen Zhao. 2021. Advances and Open Problems in Federated Learning. Foundations and Trends\u00ae in Machine Learning 14 1--2 (2021) 1--210.","DOI":"10.1561\/9781680837896"},{"key":"e_1_3_2_2_32_1","volume-title":"FederatedscopeLLM: A comprehensive package for fine-tuning large language models in federated learning. arXiv preprint arXiv:2309.00363","author":"Kuang Weirui","year":"2023","unstructured":"Weirui Kuang, Bingchen Qian, Zitao Li, Daoyuan Chen, Dawei Gao, Xuchen Pan, Yuexiang Xie, Yaliang Li, Bolin Ding, and Jingren Zhou. 2023. FederatedscopeLLM: A comprehensive package for fine-tuning large language models in federated learning. arXiv preprint arXiv:2309.00363 (2023)."},{"key":"e_1_3_2_2_33_1","volume-title":"Measuring the Intrinsic Dimension of Objective Landscapes. In International Conference on Learning Representations.","author":"Li Chunyuan","year":"2018","unstructured":"Chunyuan Li, Heerad Farkhoor, Rosanne Liu, and Jason Yosinski. 2018. Measuring the Intrinsic Dimension of Objective Landscapes. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534356"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623612"},{"key":"e_1_3_2_2_36_1","volume-title":"Proceedings of Machine learning and systems 2","author":"Li Tian","year":"2020","unstructured":"Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, and Virginia Smith. 2020. Federated optimization in heterogeneous networks. Proceedings of Machine learning and systems 2 (2020), 429--450."},{"key":"e_1_3_2_2_37_1","unstructured":"Xiang Li Kaixuan Huang Wenhao Yang Shusen Wang and Zhihua Zhang. 2019. On the Convergence of FedAvg on Non-IID Data. In ICLR."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2020.3003837"},{"key":"e_1_3_2_2_39_1","volume-title":"Fine-Tuning Language Models with Just Forward Passes. Advances in Neural Information Processing Systems","author":"Malladi Sadhika","year":"2023","unstructured":"Sadhika Malladi, Tianyu Gao, Eshaan Nichani, Alex Damian, Jason D Lee, Danqi Chen, and Sanjeev Arora. 2023. Fine-Tuning Language Models with Just Forward Passes. Advances in Neural Information Processing Systems (2023)."},{"key":"e_1_3_2_2_40_1","volume-title":"Lin (Eds.)","volume":"33","author":"Marfoq Othmane","year":"2020","unstructured":"Othmane Marfoq, Chuan Xu, Giovanni Neglia, and Richard Vidal. 2020. Throughput-Optimal Topology Design for Cross-Silo Federated Learning. In NeurIPS, H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 19478--19487. https:\/\/proceedings.neurips.cc\/ paper\/2020\/file\/e29b722e35040b88678e25a1ec032a21-Paper.pdf"},{"key":"e_1_3_2_2_41_1","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 AISTATS. PMLR 1273--1282."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"crossref","unstructured":"Chuizheng Meng Sirisha Rambhatla and Yan Liu. 2021. Cross-node federated graph neural network for spatio-temporal data modeling. In KDD. 1202--1211.","DOI":"10.1145\/3447548.3467371"},{"key":"e_1_3_2_2_43_1","volume-title":"Fedfast: Going beyond average for faster training of federated recommender systems. In KDD. 1234--1242.","author":"Muhammad Khalil","year":"2020","unstructured":"Khalil Muhammad, Qinqin Wang, Diarmuid O'Reilly-Morgan, Elias Tragos, Barry Smyth, Neil Hurley, James Geraci, and Aonghus Lawlor. 2020. Fedfast: Going beyond average for faster training of federated recommender systems. In KDD. 1234--1242."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"},{"key":"e_1_3_2_2_45_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_2_46_1","unstructured":"Zhen Qin Daoyuan Chen Bingchen Qian Bolin Ding Yaliang Li and Shuiguang Deng. 2024. Federated Full-Parameter Tuning of Billion-Sized Language Models with Communication Cost under 18 Kilobytes. arXiv:2312.06353 [cs.LG]"},{"key":"e_1_3_2_2_47_1","volume-title":"ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity. In International Conference on Learning Representations.","author":"Qiu Xinchi","year":"2022","unstructured":"Xinchi Qiu, Javier Fernandez-Marques, Pedro PB Gusmao, Yan Gao, Titouan Parcollet, and Nicholas Donald Lane. 2022. ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_48_1","volume-title":"Empirical analysis of the hessian of over-parametrized neural networks. arXiv preprint arXiv:1706.04454","author":"Sagun Levent","year":"2017","unstructured":"Levent Sagun, Utku Evci, V Ugur Guney, Yann Dauphin, and Leon Bottou. 2017. Empirical analysis of the hessian of over-parametrized neural networks. arXiv preprint arXiv:1706.04454 (2017)."},{"key":"e_1_3_2_2_49_1","volume-title":"Clustered Federated Learning: Model-Agnostic Distributed Multitask Optimization Under Privacy Constraints. TNNLS","author":"Sattler Felix","year":"2020","unstructured":"Felix Sattler, Klaus-Robert M\u00fcller, and Wojciech Samek. 2020. Clustered Federated Learning: Model-Agnostic Distributed Multitask Optimization Under Privacy Constraints. TNNLS (2020)."},{"key":"e_1_3_2_2_50_1","volume-title":"Federated Zeroth-Order Optimization using Trajectory-Informed Surrogate Gradients. arXiv preprint arXiv:2308.04077","author":"Shu Yao","year":"2023","unstructured":"Yao Shu, Xiaoqiang Lin, Zhongxiang Dai, and Bryan Kian Hsiang Low. 2023. Federated Zeroth-Order Optimization using Trajectory-Informed Surrogate Gradients. arXiv preprint arXiv:2308.04077 (2023)."},{"key":"e_1_3_2_2_51_1","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."},{"key":"e_1_3_2_2_52_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_53_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_54_1","volume-title":"Deepesh Data, et al","author":"Wang Jianyu","year":"2021","unstructured":"Jianyu Wang, Zachary Charles, Zheng Xu, Gauri Joshi, H Brendan McMahan, Maruan Al-Shedivat, Galen Andrew, Salman Avestimehr, Katharine Daly, Deepesh Data, et al. 2021. A field guide to federated optimization. arXiv preprint arXiv:2107.06917 (2021)."},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2021.3106104"},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539112"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.14778\/3579075.3579081"},{"key":"e_1_3_2_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData50022.2020.9378171"},{"key":"e_1_3_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110353"},{"key":"e_1_3_2_2_61_1","volume-title":"Towards Building the Federated GPT: Federated Instruction Tuning. arXiv preprint arXiv:2305.05644","author":"Zhang Jianyi","year":"2023","unstructured":"Jianyi Zhang, Saeed Vahidian, Martin Kuo, Chunyuan Li, Ruiyi Zhang, Guoyin Wang, and Yiran Chen. 2023. Towards Building the Federated GPT: Federated Instruction Tuning. arXiv preprint arXiv:2305.05644 (2023)."},{"key":"e_1_3_2_2_62_1","volume-title":"Towards Building the FederatedGPT: Federated Instruction Tuning. In International Workshop on Federated Learning in the Age of Foundation Models in Conjunction with NeurIPS","author":"Zhang Jianyi","year":"2023","unstructured":"Jianyi Zhang, Saeed Vahidian, Martin Kuo, Chunyuan Li, Ruiyi Zhang, Tong Yu, Guoyin Wang, and Yiran Chen. 2023. Towards Building the FederatedGPT: Federated Instruction Tuning. In International Workshop on Federated Learning in the Age of Foundation Models in Conjunction with NeurIPS 2023. https:\/\/ openreview.net\/forum?id=TaDiklyVps"},{"key":"e_1_3_2_2_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482249"},{"key":"e_1_3_2_2_64_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."},{"key":"e_1_3_2_2_65_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223 (2023)."}],"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\/3637528.3671865","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671865","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T20:04:14Z","timestamp":1750277054000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671865"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":65,"alternative-id":["10.1145\/3637528.3671865","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671865","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"}}]}}