Communication-Efficient Learning of Deep Networksfrom Decentralized Data标题: Communication-Efficient Learning of Deep Networks from Decentralized Data
作者:
H. Brendan McMahan
Eider Moore
Daniel Ramage
Seth Hampson
Blaise Agüera y Arcas
机构: Google, Inc., 651 N 34th St., Seattle, WA 98103 USA
发表会议:
ICML 2024:Fine-Tuning Large Language Models with User-Level Differential Privacy
基本信息
标题: Fine-Tuning Large Language Models with User-Level Differential Privacy
作者:
Zachary Charles, Google Research, Seattle, WA, USA, zachcharles@google.com
Arun Ganesh, Google Research, Seattle, WA, USA, arunganesh@google.com
Ryan McKenna, Google Research, Seattle, WA, USA, mckennar@google.com
基本信息
标题：Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization
作者：
Tianshi Che (Auburn University, Auburn, United States)
Ji Liu (Hithink RoyalFlush Information Network Co., Ltd., Hangzhou, Zhejiang, China)
Yang Zhou (Auburn University, Auburn,
基本信息
标题：PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs
作者：Charlie Hou, Akshat Shrivastava, Hongyuan Zhan, Rylan Conway, Trang Le, Adithya Sagar, Giulia Fanti, Daniel Lazar
机构：
Charlie Hou, Giulia Fanti：Carnegie Mellon University, Department of Electrical and Comput
基本信息
标题: FedBiOT: LLM Local Fine-tuning in Federated Learning without Full Model
作者:
Feijie Wu (Purdue University, wu1977@purdue.edu)
Zitao Li (Alibaba Group, zitao.l@alibaba-inc.com)
Yaliang Li (Alibaba Group, yaliang.li@alibaba-inc.com)
Bolin Ding (Alibaba Group, bolin.ding@alibaba-inc.com)
Jing
基本信息
标题:
EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning & Voting
作者:
Zhongzhi Yu, Zheng Wang, Yuhan Li, Haoran You, Ruijie Gao, Xiaoya Zhou, Sreenidhi Reedy Bommu, Yang (Katie) Zhao, Yingyan (Celine) Lin
作
基本信息
标题: SPT: Fine-Tuning Transformer-based Language Models Efficiently with Sparsification
作者: Yuntao Gui, Xiao Yan, Peiqi Yin, Han Yang, James Cheng
机构:
The Chinese University of Hong Kong, Hong Kong SAR, China
Southern University of Science and Technology, China
关键词: language models, transforme
