MLSP-P10.2

FAVANO: FEDERATED AVERAGING WITH ASYNCHRONOUS NODES

Louis Leconte, Sorbonne & Huawei, France; Van Minh Nguyen, Huawei France, France; Eric Moulines, Ecole Polytechnique, France

Session:
MLSP-P10: Distributed and Federated Learning II Poster

Track:
Machine Learning for Signal Processing

Location:
Poster Zone 3B
Poster Board PZ-3B.2

Presentation Time:
Wed, 17 Apr, 08:20 - 10:20 (UTC +9)

Session Chair:
Sheng Li, National Institute of Information and Communications Technology (NICT) Japan
View Manuscript
Presentation
Discussion
Resources
Session MLSP-P10
MLSP-P10.1: TOWARDS RESOURCE-EFFICIENT AND SECURE FEDERATED MULTIMEDIA RECOMMENDATION
Guohui Li, Xuanang Ding, Ling Yuan, Lu Zhang, Qian Rong, Huazhong University of Science and Technology, China
MLSP-P10.2: FAVANO: FEDERATED AVERAGING WITH ASYNCHRONOUS NODES
Louis Leconte, Sorbonne & Huawei, France; Van Minh Nguyen, Huawei France, France; Eric Moulines, Ecole Polytechnique, France
MLSP-P10.3: COMMUNICATION-EFFICIENT FEDERATED LEARNING THROUGH ADAPTIVE WEIGHT CLUSTERING AND SERVER-SIDE DISTILLATION
Vasileios Tsouvalas, Aaqib Saeed, Tanir Ozcelebi, Nirvana Meratnia, Eindhoven University of Technology, Netherlands
MLSP-P10.4: TOPOLOGY-DEPENDENT PRIVACY BOUND FOR DECENTRALIZED FEDERATED LEARNING
Qiongxiu Li, Tsinghua University, China; Wenrui Yu, Delft University of Technology, Netherlands; Changlong Ji, Telecom SudParis, Institut Polytechnique de Paris, France; Richard Heusdens, Netherlands Defence Academy, Delft University of Technology, Netherlands
MLSP-P10.5: FEDERATED PAC-BAYESIAN LEARNING ON NON-IID DATA
Zihao Zhao, Tsinghua-Berkeley Shenzhen Institute, China; Yang Liu, Institute for AI Industry Research, Shanghai Artificial Intelligence Laboratory, China; Wenbo Ding, Tsinghua-Berkeley Shenzhen Institute, Shanghai Artificial Intelligence Laboratory, China; Xiao-Ping Zhang, Tsinghua-Berkeley Shenzhen Institute, China
MLSP-P10.6: MISA: UNVEILING THE VULNERABILITIES IN SPLIT FEDERATED LEARNING
Wei Wan, Yuxuan Ning, Shengshan Hu, Lulu Xue, Minghui Li, Huazhong University of Science and Technology, China; Leo Yu Zhang, Griffith University, Australia; Hai Jin, Huazhong University of Science and Technology, China
MLSP-P10.7: PROMPTING LABEL EFFICIENCY IN FEDERATED GRAPH LEARNING VIA PERSONALIZED SEMI-SUPERVISION
Qinghua Mao, Xi Lin, Shanghai Jiao Tong University, China; Xiu Su, The University of Sydney, Australia; Gaolei Li, Lixing Chen, Jianhua Li, Shanghai Jiao Tong University, China
MLSP-P10.8: Towards Building the FederatedGPT: Federated Instruction Tuning
Jianyi Zhang, Saeed Vahidian, Martin Kuo, Duke University, United States of America; Chunyuan Li, Microsoft Research, United States of America; Ruiyi Zhang, Tong Yu, Adobe Research, United States of America; Guoyin Wang, Amazon, United States of America; Yiran Chen, Duke University, United States of America
MLSP-P10.9: DISTRIBUTED STOCHASTIC CONTEXTUAL BANDITS FOR PROTEIN DRUG INTERACTION
Jiabin Lin, Karuna Anna Sajeevan, Bibek Acharya, Shana Moothedath, Ratul Chowdhury, Iowa State University, United States of America
MLSP-P10.10: DIFFERENTIALLY PRIVATE FEDERATED FRANK-WOLFE
Robin Francis, Sundeep Prabhakar Chepuri, Indian Institute of Science, Bangalore, India
MLSP-P10.11: Federated Learning on Distributed Graphs considering Multiple Heterogeneities
Baiqi Li, Yedi Ma, Yufei Liu, Hongyan Gu, East China Normal University, China; Zhenghan Chen, Peking University, China; XinLi Huang, East China Normal University, China
MLSP-P10.12: A STOCHASTIC GRADIENT APPROACH FOR COMMUNICATION EFFICIENT CONFEDERATED LEARNING
Bin Wang, Jun Fang, University of Electronic Science and Technology of China, China; Hongbin Li, Stevens Institute of Technology, United States of America; Yonina Eldar, Weizmann Institute of Science, Israel
Contacts