MLSP-P33.1
FEDAQT: ACCURATE QUANTIZED TRAINING WITH FEDERATED LEARNING
Renkun Ni, University of Maryland, United States of America; Yonghui Xiao, Phoenix Meadowlark, Oleg Rybakov, Google, United States of America; Tom Goldstein, University of Maryland, United States of America; Ananda Theertha Suresh, Ignacio Lopez Moreno, Mingqing Chen, Rajiv Mathews, Google, United States of America
Session:
MLSP-P33: Distributed and Federated Learning III Poster
Track:
Machine Learning for Signal Processing
Location:
Poster Zone 3B
Poster Board PZ-3B.1
Poster Board PZ-3B.1
Presentation Time:
Fri, 19 Apr, 08:20 - 10:20 (UTC +9)
Session Chair:
Wenwu Wang, University of Surrey
Session MLSP-P33
MLSP-P33.1: FEDAQT: ACCURATE QUANTIZED TRAINING WITH FEDERATED LEARNING
Renkun Ni, University of Maryland, United States of America; Yonghui Xiao, Phoenix Meadowlark, Oleg Rybakov, Google, United States of America; Tom Goldstein, University of Maryland, United States of America; Ananda Theertha Suresh, Ignacio Lopez Moreno, Mingqing Chen, Rajiv Mathews, Google, United States of America
MLSP-P33.2: DISENTANGLE ESTIMATION OF CAUSAL EFFECTS FROM CROSS-SILO DATA
Yuxuan Liu, University of Electronic Science and Technology of China, China; Haozhao Wang, Huazhong University of Science and Technology, China; Shuang Wang, Nuowei Technology, China; Zhiming He, University of Electronic Science and Technology of China, China; Wenchao Xu, The Hong Kong Polytechnic University, China; Jialiang Zhu, University of Electronic Science and Technology of China, China; Fan Yang, Inner Mongolia Normal University, China
MLSP-P33.3: 3D PARALLELISM FOR TRANSFORMERS VIA INTEGER PROGRAMMING
Hao Zheng, Peng Liang, Yu Tang, Yanqi Shi, Linbo Qiao, Dongsheng Li, National University of Defense Technology, China
MLSP-P33.4: PERSONALIZED LOCAL DIFFERENTIALLY PRIVATE FEDERATED LEARNING WITH ADAPTIVE CLIENT SAMPLING
Yizhou Chen, Wangjie Xu, Xincheng Wu, Meng Zhang, Zhejiang University, China; Bing Luo, Duke Kunshan University, China
MLSP-P33.5: ADAFL: ADAPTIVE CLIENT SELECTION AND DYNAMIC CONTRIBUTION EVALUATION FOR EFFICIENT FEDERATED LEARNING
Qingming Li, Research Institute of Artificial Intelligence, Zhejiang Lab, China; Xiaohang Li, Nanjing University of Aeronautics and Astronautics, China; Li Zhou, Xiaoran Yan, Research Institute of Artificial Intelligence, Zhejiang Lab, China
MLSP-P33.6: PRIVACY PRESERVING FEDERATED LEARNING FROM MULTI-INPUT FUNCTIONAL PROXY RE-ENCRYPTION
Xinyu Feng, Qingni Shen, Cong Li, Yuejian Fang, Zhonghai Wu, Peking University, China
MLSP-P33.7: COMMUNICATION-EFFICIENT DECENTRALIZED DYNAMIC KERNEL LEARNING
Ping Xu, The University of Texas Rio Grande Valley, United States of America; Yue Wang, Georgia State University, United States of America; Xiang Chen, Zhi Tian, George Mason University, United States of America
MLSP-P33.8: TREE NETWORK DESIGN FOR FASTER DISTRIBUTED MACHINE LEARNING PROCESS WITH DISTRIBUTED DUAL COORDINATE ASCENT
Myung Cho, Meghana Chikkam, California State University, Northridge, United States of America; Weiyu Xu, University of Iowa, United States of America; Lifeng Lai, University of California, Davis, United States of America
MLSP-P33.9: Mutual information based Noise Scale optimization for Gradient Leakage Resistant Federated Learning
Chao Zheng, Institute of Information Engineering, Chinese Academy of Sciences;School of Cyber Security, University of Chinese Academy of Sciences, China; Liming Wang, Zhen Xu, Hongjia Li, Institute of Information Engineering, Chinese Academy of Sciences, China
Contacts