MLSP-42.5
Byzantine-Robust Aggregation with Gradient Difference Compression and Stochastic Variance Reduction for Federated Learning
Heng Zhu, University of California, San Diego, United States of America; Qing Ling, Sun Yat-Sen University, China
Session:
Distributed and Federated Learning I
Track:
Machine Learning for Signal Processing
Location:
Gather Area H
Presentation Time:
Thu, 12 May, 20:00 - 20:45 China Time (UTC +8)
Thu, 12 May, 12:00 - 12:45 UTC
Thu, 12 May, 12:00 - 12:45 UTC
Session Chair:
Jie Ding, University of Minnesota and Alexa AI, Amazon
Session MLSP-42
MLSP-42.1: SOCIAL WELFARE MAXIMIZATION IN CROSS-SILO FEDERATED LEARNING
Jianan Chen, Qin Hu, Indiana University Purdue University Indianapolis, United States of America; Honglu Jiang, The University of Texas Rio Grande Valley, United States of America
MLSP-42.2: PRIVACY-PRESERVING DISTRIBUTED EXPECTATION MAXIMIZATION FOR GAUSSIAN MIXTURE MODEL USING SUBSPACE PERTURBATION
Qiongxiu Li, Jaron Skovsted Gundersen, Katrine Tjell, Rafal Wisniewski, Mads Græsbøll Christensen, Aalborg university, Denmark
MLSP-42.3: A COMMUNICATION EFFICIENT QUASI-NEWTON METHOD FOR LARGE-SCALE DISTRIBUTED MULTI-AGENT OPTIMIZATION
Yichuan Li, University of Illinois Urbana Champaign, United States of America; Petros Voulgaris, University of Nevada, Reno, United States of America; Nikolaos Freris, University of Science and Technology of China, China
MLSP-42.4: A Byzantine-resilient Dual Subgradient Method for Vertical Federated Learning
Kun Yuan, Alibaba Group (US), United States of America; Zhaoxian Wu, Qing Ling, Sun Yat-Sen University, China
MLSP-42.5: Byzantine-Robust Aggregation with Gradient Difference Compression and Stochastic Variance Reduction for Federated Learning
Heng Zhu, University of California, San Diego, United States of America; Qing Ling, Sun Yat-Sen University, China
MLSP-42.6: VARIANCE REDUCTION-BOOSTED BYZANTINE ROBUSTNESS IN DECENTRALIZED STOCHASTIC OPTIMIZATION
Jie Peng, Qing Ling, Sun Yat-Sen University, China; Weiyu Li, Harvard Univeristy, China