{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T16:56:34Z","timestamp":1784134594504,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":70,"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\/3637528.3671573","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:54:55Z","timestamp":1724561695000},"page":"5260-5271","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":121,"title":["FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8544-0221","authenticated-orcid":false,"given":"Weirui","family":"Kuang","sequence":"first","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3177-3249","authenticated-orcid":false,"given":"Bingchen","family":"Qian","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"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\/0000-0002-8015-2121","authenticated-orcid":false,"given":"Daoyuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3882-5189","authenticated-orcid":false,"given":"Dawei","family":"Gao","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0081-5405","authenticated-orcid":false,"given":"Xuchen","family":"Pan","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6545-7882","authenticated-orcid":false,"given":"Yuexiang","family":"Xie","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, 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, Hangzhou, China"}],"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\/0000-0002-4220-2634","authenticated-orcid":false,"given":"Jingren","family":"Zhou","sequence":"additional","affiliation":[{"name":"Alibaba Group, Bellevue, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Anthropic. 2023. Introducing Claude."},{"key":"e_1_3_2_2_2_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_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/2188385.2188395"},{"key":"e_1_3_2_2_4_1","volume-title":"Proc. of machine learning and systems (MLSys'19)","volume":"1","author":"Bonawitz Keith","year":"2019","unstructured":"Keith Bonawitz, Hubert Eichner, Wolfgang Grieskamp, et al. 2019. Towards federated learning at scale: System design. In Proc. of machine learning and systems (MLSys'19), Vol. 1. 374--388."},{"key":"e_1_3_2_2_5_1","volume-title":"Proc. of the Advances in Neural Information Processing Systems (NeurIPS'20)","volume":"33","author":"Brown Tom","year":"2020","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. In Proc. of the Advances in Neural Information Processing Systems (NeurIPS'20), Vol. 33. 1877--1901."},{"key":"e_1_3_2_2_6_1","volume-title":"Peter Wu, Tian Li, Jakub Konevcn\u1ef3, H Brendan McMahan, Virginia Smith, and Ameet Talwalkar.","author":"Caldas Sebastian","year":"2018","unstructured":"Sebastian Caldas, Sai Meher Karthik Duddu, Peter Wu, Tian Li, Jakub Konevcn\u1ef3, H Brendan McMahan, Virginia Smith, and Ameet Talwalkar. 2018. Leaf: A benchmark for federated settings. arXiv preprint arXiv:1812.01097 (2018)."},{"key":"e_1_3_2_2_7_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_8_1","volume-title":"Proc. of the Advances in Neural Information Processing Systems (NeurIPS'22)","volume":"35","author":"Chen Daoyuan","year":"2022","unstructured":"Daoyuan Chen, Dawei Gao, Weirui Kuang, Yaliang Li, and Bolin Ding. 2022. pFL-Bench: A Comprehensive Benchmark for Personalized Federated Learning. In Proc. of the Advances in Neural Information Processing Systems (NeurIPS'22), Vol. 35. 9344--9360."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599829"},{"key":"e_1_3_2_2_10_1","unstructured":"Mark Chen Jerry Tworek Heewoo Jun et al. 2021. Evaluating Large Language Models Trained on Code. arXiv perprint arXiv:2107.03374 (2021)."},{"key":"e_1_3_2_2_11_1","unstructured":"Aakanksha Chowdhery Sharan Narang Jacob Devlin et al. 2022. PaLM: Scaling Language Modeling with Pathways. arXiv preprint arXiv:2204.02311 (2022)."},{"key":"e_1_3_2_2_12_1","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian et al. 2021. Training Verifiers to Solve Math Word Problems. arXiv preprint arXiv:2110.14168 (2021)."},{"key":"e_1_3_2_2_13_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_14_1","volume-title":"Proc. of the Advances in Neural Information Processing Systems (NeurIPS'20)","volume":"33","author":"Dai Zhongxiang","year":"2020","unstructured":"Zhongxiang Dai, Bryan Kian Hsiang Low, and Patrick Jaillet. 2020. Federated Bayesian Optimization via Thompson Sampling. In Proc. of the Advances in Neural Information Processing Systems (NeurIPS'20), Vol. 33. 9687--9699."},{"key":"e_1_3_2_2_15_1","volume-title":"1996 a. DEFLATE Compressed Data Format Specification version 1.3","author":"Deutsch L. Peter","unstructured":"L. Peter Deutsch. 1996 a. DEFLATE Compressed Data Format Specification version 1.3. RFC. Network Working Group."},{"key":"e_1_3_2_2_16_1","volume-title":"1996 b. GZIP file format specification version 4.3","author":"Deutsch L. Peter","unstructured":"L. Peter Deutsch. 1996 b. GZIP file format specification version 4.3. RFC. Network Working Group."},{"key":"e_1_3_2_2_17_1","volume-title":"Proc. of NAACL-HLT (NAACL-HLT'19)","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In Proc. of NAACL-HLT (NAACL-HLT'19). 4171--4186."},{"key":"e_1_3_2_2_18_1","volume-title":"Collaborating Heterogeneous Natural Language Processing Tasks via Federated Learning. arXiv preprint arXiv:2212.05789","author":"Dong Chenhe","year":"2022","unstructured":"Chenhe Dong, Yuexiang Xie, Bolin Ding, Ying Shen, and Yaliang Li. 2022. Collaborating Heterogeneous Natural Language Processing Tasks via Federated Learning. arXiv preprint arXiv:2212.05789 (2022)."},{"key":"e_1_3_2_2_19_1","volume-title":"Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, et al.","author":"Driess Danny","year":"2023","unstructured":"Danny Driess, Fei Xia, Mehdi SM Sajjadi, Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, et al. 2023. PaLM-E: An Embodied Multimodal Language Model. arXiv preprint arXiv:2303.03378 (2023)."},{"key":"e_1_3_2_2_20_1","first-page":"4046","article-title":"FS-Real","volume":"16","author":"Gao Dawei","year":"2023","unstructured":"Dawei Gao, Daoyuan Chen, Zitao Li, Yuexiang Xie, Xuchen Pan, Yaliang Li, Bolin Ding, and Jingren Zhou. 2023. FS-Real: A Real-World Cross-Device Federated Learning Platform. PVLDB, Vol. 16 (2023), 4046--4049.","journal-title":"A Real-World Cross-Device Federated Learning Platform. PVLDB"},{"key":"e_1_3_2_2_21_1","volume-title":"Proc. of the International Conference on Machine Learning (ICML'21)","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-Efficient Transfer Learning for NLP. In Proc. of the International Conference on Machine Learning (ICML'21). 2790--2799."},{"key":"e_1_3_2_2_22_1","volume-title":"Proc. of the International Conference on Learning Representations (ICLR'22)","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In Proc. of the International Conference on Learning Representations (ICLR'22)."},{"key":"e_1_3_2_2_23_1","volume-title":"Qiang Liu, et al.","author":"Huang Shaohan","year":"2023","unstructured":"Shaohan Huang, Li Dong, Wenhui Wang, Yaru Hao, Saksham Singhal, Shuming Ma, Tengchao Lv, Lei Cui, Owais Khan Mohammed, Qiang Liu, et al. 2023. Language Is Not All You Need: Aligning Perception with Language Models. arXiv preprint arXiv:2302.14045 (2023)."},{"key":"e_1_3_2_2_24_1","volume-title":"Creative Writing with an AI-Powered Writing Assistant: Perspectives from Professional Writers. arXiv preprint arXiv:2211.05030","author":"Ippolito Daphne","year":"2022","unstructured":"Daphne Ippolito, Ann Yuan, Andy Coenen, and Sehmon Burnam. 2022. Creative Writing with an AI-Powered Writing Assistant: Perspectives from Professional Writers. arXiv preprint arXiv:2211.05030 (2022)."},{"key":"e_1_3_2_2_25_1","volume-title":"Proc. of the Artificial intelligence and statistics (AISTATS'16)","author":"Jamieson Kevin","year":"2016","unstructured":"Kevin Jamieson and Ameet Talwalkar. 2016. Non-stochastic Best Arm Identification and Hyperparameter Optimization. In Proc. of the Artificial intelligence and statistics (AISTATS'16). 240--248."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3571730"},{"key":"e_1_3_2_2_27_1","volume-title":"Proc. of the Advances in Neural Information Processing Systems (NeurIPS'21)","volume":"34","author":"Mahabadi Rabeeh Karimi","year":"2021","unstructured":"Rabeeh Karimi Mahabadi, James Henderson, and Sebastian Ruder. 2021. Compacter: Efficient Low-Rank Hypercomplex Adapter Layers. In Proc. of the Advances in Neural Information Processing Systems (NeurIPS'21), Vol. 34. 1022--1035."},{"key":"e_1_3_2_2_28_1","volume-title":"Federated Optimization: Distributed Machine Learning for On-Device Intelligence. arXiv preprint arXiv:1610.02527","author":"Konevcn\u00fd Jakub","year":"2016","unstructured":"Jakub Konevcn\u00fd, H. Brendan McMahan, Daniel Ramage, and Peter Richt\u00e1rik. 2016. Federated Optimization: Distributed Machine Learning for On-Device Intelligence. arXiv preprint arXiv:1610.02527 (2016)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"crossref","unstructured":"Weirui Kuang Bingchen Qian Zitao Li Daoyuan Chen Dawei Gao Xuchen Pan Yuexiang Xie Yaliang Li Bolin Ding and Jingren Zhou. 2023. FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning. arxiv: 2309.00363","DOI":"10.1145\/3637528.3671573"},{"key":"e_1_3_2_2_30_1","volume-title":"Proc. of the International Conference on Machine Learning (ICML'22)","volume":"162","author":"Lai Fan","year":"2022","unstructured":"Fan Lai, Yinwei Dai, Sanjay Singapuram, Jiachen Liu, Xiangfeng Zhu, Harsha Madhyastha, and Mosharaf Chowdhury. 2022. FedScale: Benchmarking Model and System Performance of Federated Learning at Scale. In Proc. of the International Conference on Machine Learning (ICML'22), Vol. 162. 11814--11827."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3502030"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"e_1_3_2_2_33_1","volume-title":"Proc. of the International Conference on Machine Learning (ICML'21)","volume":"139","author":"Li Tian","year":"2021","unstructured":"Tian Li, Shengyuan Hu, Ahmad Beirami, and Virginia Smith. 2021. Ditto: Fair and Robust Federated Learning Through Personalization. In Proc. of the International Conference on Machine Learning (ICML'21), Vol. 139. 6357--6368."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"e_1_3_2_2_35_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_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671865"},{"key":"e_1_3_2_2_37_1","volume-title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks. arXiv preprint arXiv:2110.07602","author":"Liu Xiao","year":"2021","unstructured":"Xiao Liu, Kaixuan Ji, Yicheng Fu, Zhengxiao Du, Zhilin Yang, and Jie Tang. 2021. P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks. arXiv preprint arXiv:2110.07602 (2021)."},{"key":"e_1_3_2_2_38_1","volume-title":"arXiv preprint arXiv:2103.10385","author":"Liu Xiao","year":"2021","unstructured":"Xiao Liu, Yanan Zheng, Zhengxiao Du, Ming Ding, Yujie Qian, Zhilin Yang, and Jie Tang. 2021. GPT Understands, Too. arXiv preprint arXiv:2103.10385 (2021)."},{"key":"e_1_3_2_2_39_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_2_40_1","volume-title":"PEFT: State-of-the-art Parameter-Efficient Fine-Tuning methods. https:\/\/github.com\/huggingface\/peft.","author":"Mangrulkar Sourab","year":"2022","unstructured":"Sourab Mangrulkar, Sylvain Gugger, Lysandre Debut, Younes Belkada, and Sayak Paul. 2022. PEFT: State-of-the-art Parameter-Efficient Fine-Tuning methods. https:\/\/github.com\/huggingface\/peft."},{"key":"e_1_3_2_2_41_1","volume-title":"Proc. of the Artificial intelligence and statistics (AISTATS'17)","author":"McMahan H. Brendan","year":"2017","unstructured":"H. Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Ag\u00fcera y Arcas. 2017. Communication-Efficient Learning of Deep Networks from Decentralized Data. In Proc. of the Artificial intelligence and statistics (AISTATS'17). 1273--1282."},{"key":"e_1_3_2_2_42_1","volume-title":"Proc. of the International Conference on Learning Representations (ICLR'18)","author":"Micikevicius Paulius","year":"2018","unstructured":"Paulius Micikevicius, Sharan Narang, Jonah Alben, Gregory Diamos, Erich Elsen, David Garcia, Boris Ginsburg, Michael Houston, Oleksii Kuchaiev, Ganesh Venkatesh, et al. 2018. Mixed Precision Training. In Proc. of the International Conference on Learning Representations (ICLR'18)."},{"key":"e_1_3_2_2_43_1","unstructured":"OpenAI. 2022. Introducing ChatGPT."},{"key":"e_1_3_2_2_45_1","volume-title":"Proc. of the Advances in Neural Information Processing Systems (NeurIPS'19)","volume":"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. In Proc. of the Advances in Neural Information Processing Systems (NeurIPS'19), Vol. 32. 8024--8035."},{"key":"e_1_3_2_2_46_1","volume-title":"Gonzalez","author":"Patil Shishir G.","year":"2023","unstructured":"Shishir G. Patil, Tianjun Zhang, Xin Wang, and Joseph E. Gonzalez. 2023. Gorilla: Large Language Model Connected with Massive APIs. arXiv preprint arXiv:2305.15334 (2023)."},{"key":"e_1_3_2_2_47_1","volume-title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning. arXiv preprint arXiv:2005.00247","author":"Pfeiffer Jonas","year":"2020","unstructured":"Jonas Pfeiffer, Aishwarya Kamath, Andreas R\u00fcckl\u00e9, Kyunghyun Cho, and Iryna Gurevych. 2020. AdapterFusion: Non-Destructive Task Composition for Transfer Learning. arXiv preprint arXiv:2005.00247 (2020)."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.617"},{"key":"e_1_3_2_2_49_1","unstructured":"Yujia Qin Shihao Liang Yining Ye Kunlun Zhu Lan Yan Yaxi Lu Yankai Lin Xin Cong Xiangru Tang Bill Qian et al. 2023. ToolLLM: Facilitating Large Language Models to Master 16000 Real-world APIs. arXiv preprint arXiv:2307.16789 (2023)."},{"key":"e_1_3_2_2_50_1","volume-title":"International Conference on Machine Learning.","author":"Qin Zhen","year":"2024","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. In International Conference on Machine Learning."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3406703"},{"key":"e_1_3_2_2_52_1","volume-title":"Proc. of the USENIX Annual Technical Conference (USENIX ATC'21)","author":"Ren Jie","year":"2021","unstructured":"Jie Ren, Samyam Rajbhandari, Reza Yazdani Aminabadi, Olatunji Ruwase, Shuangyang Yang, Minjia Zhang, Dong Li, and Yuxiong He. 2021. ZeRO-Offload: Democratizing Billion-Scale Model Training. In Proc. of the USENIX Annual Technical Conference (USENIX ATC'21). 551--564."},{"key":"e_1_3_2_2_53_1","unstructured":"Gene Ruebsamen. 2023. Cleaned Alpaca Dataset. https:\/\/github.com\/gururise\/AlpacaDataCleaned."},{"key":"e_1_3_2_2_54_1","volume-title":"A generic framework for privacy preserving deep learning. arXiv preprint arXiv:1811.04017","author":"Ryffel Th\u00e9o","year":"2018","unstructured":"Th\u00e9o Ryffel, Andrew Trask, Morten Dahl, Bobby Wagner, Jason V. Mancuso, Daniel Rueckert, and Jonathan Passerat-Palmbach. 2018. A generic framework for privacy preserving deep learning. arXiv preprint arXiv:1811.04017 (2018)."},{"key":"e_1_3_2_2_55_1","volume-title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model. arXiv preprint arXiv:2211.05100","author":"Scao Teven Le","year":"2022","unstructured":"Teven Le Scao, Angela Fan, Christopher Akiki, et al. 2022. BLOOM: A 176B-Parameter Open-Access Multilingual Language Model. arXiv preprint arXiv:2211.05100 (2022)."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494218"},{"key":"e_1_3_2_2_57_1","volume-title":"Proc. of the Advances in Neural Information Processing Systems (NeurIPS'20)","volume":"33","author":"Dinh Canh T","year":"2020","unstructured":"Canh T Dinh, Nguyen Tran, and Josh Nguyen. 2020. Personalized Federated Learning with Moreau Envelopes. In Proc. of the Advances in Neural Information Processing Systems (NeurIPS'20), Vol. 33. 21394--21405."},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3160699"},{"key":"e_1_3_2_2_59_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_60_1","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard et al. 2023. LLaMA: Open and Efficient Foundation Language Models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539112"},{"key":"e_1_3_2_2_62_1","volume-title":"Proc. of the International Conference on Machine Learning (ICML'23)","author":"Wang Zhen","year":"2023","unstructured":"Zhen Wang, Weirui Kuang, Ce Zhang, Bolin Ding, and Yaliang Li. 2023. FedHPO-Bench: A Benchmark Suite for Federated Hyperparameter Optimization. In Proc. of the International Conference on Machine Learning (ICML'23). 35908--35948."},{"key":"e_1_3_2_2_63_1","volume-title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models. arXiv preprint arXiv:2303.04671","author":"Wu Chenfei","year":"2023","unstructured":"Chenfei Wu, Sheng-Kai Yin, Weizhen Qi, Xiaodong Wang, Zecheng Tang, and Nan Duan. 2023. Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models. arXiv preprint arXiv:2303.04671 (2023)."},{"key":"e_1_3_2_2_64_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_65_1","doi-asserted-by":"publisher","DOI":"10.14778\/3579075.3579081"},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01585-4"},{"key":"e_1_3_2_2_67_1","volume-title":"Proc. of the International Conference on Learning Representations (ICLR'23)","author":"Zeng Aohan","year":"2023","unstructured":"Aohan Zeng, Xiao Liu, Zhengxiao Du, Zihan Wang, Hanyu Lai, Ming Ding, Zhuoyi Yang, Yifan Xu, Wendi Zheng, Xiao Xia, et al. 2023. GLM-130B: An Open Bilingual Pre-trained Model. In Proc. of the International Conference on Learning Representations (ICLR'23)."},{"key":"e_1_3_2_2_68_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_69_1","volume-title":"Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers. arXiv preprint arXiv:1911.00361","author":"Zhang Xishan","year":"2019","unstructured":"Xishan Zhang, Shaoli Liu, Rui Zhang, Chang Liu, Di Huang, Shiyi Zhou, Jiaming Guo, Yu Kang, Qi Guo, Zidong Du, and Yunji Chen. 2019. Adaptive Precision Training: Quantify Back Propagation in Neural Networks with Fixed-point Numbers. arXiv preprint arXiv:1911.00361 (2019)."},{"key":"e_1_3_2_2_70_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)."},{"key":"e_1_3_2_2_71_1","volume-title":"Proc. of the International Conference on Learning Representations (ICLR'23)","author":"Zhou Yi","year":"2023","unstructured":"Yi Zhou, Parikshit Ram, Theodoros Salonidis, Nathalie Baracaldo, Horst Samulowitz, and Heiko Ludwig. 2023. Single-shot Hyper-parameter Optimization for Federated Learning. In Proc. of the International Conference on Learning Representations (ICLR'23)."}],"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\/3637528.3671573","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671573","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:04:19Z","timestamp":1750291459000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671573"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":70,"alternative-id":["10.1145\/3637528.3671573","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671573","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"}}]}}