MLSP-L31.1
When Differential Privacy Meets Wireless Federated Learning: An Improved Analysis for Privacy and Convergence
Yaoling Chen, Xiamen University, China; Hao Liang, Hong Kong University of Science and Technology (Guangzhou), China; Xiaotong Tu, Xiamen University, China
Session:
MLSP-L31: Optimization and Privacy in Federated Learning Oral
Track:
Machine Learning for Signal Processing [ML]
Location:
Room 112
Presentation Time:
Fri, 8 May, 14:00 - 14:20
Presentation
Discussion
Resources
No resources available.
Session MLSP-L31
MLSP-L31.1: When Differential Privacy Meets Wireless Federated Learning: An Improved Analysis for Privacy and Convergence
Yaoling Chen, Xiamen University, China; Hao Liang, Hong Kong University of Science and Technology (Guangzhou), China; Xiaotong Tu, Xiamen University, China
MLSP-L31.2: DIFFERENTIABLE META-OPTIMIZATION FOR FEDERATED NEURAL ARCHITECTURE SEARCH
Xinyuan Huang, University of Toronto, Canada; Jiechao Gao, Stanford University, United States of America; Tiange Xie, Institute of Information Engineering, Chinese Academy of Sciences, China
MLSP-L31.3: FEDPROLN: CLASS PROTOTYPE-ENHANCED FEDERATED LEARNING FOR LONG-TAILED NOISY LABELS
Xiangyu Han, Yuanguo Bi, Xinhui Lin, Tianao Xiang, Yixuan Tong, Northeastern University, China
MLSP-L31.4: FED-GAME: PERSONALIZED FEDERATED LEARNING WITH GRAPH ATTENTION MIXTURE-OF-EXPERTS FOR TIME-SERIES FORECASTING
Yi Li, Central South University, China; Han Liu, Mingfeng Fan, National University of Singapore, Singapore; Guo Chen, University of New South Wales, Australia; Chaojie Li, City University of Hong Kong, China; Biplab Sikdar, National University of Singapore, Singapore
MLSP-L31.5: DIFFERENTIALLY PRIVATE CLUSTERED FEDERATED LEARNING WITH PRIVACY-PRESERVING INITIALIZATION AND NORMALITY-DRIVEN AGGREGATION
Jie Xu, Haaris Mehmood, Samsung R&D Institute UK (SRUK), United Kingdom of Great Britain and Northern Ireland; Rogier Van Dalen, Samsung AI Centre Cambridge, United Kingdom of Great Britain and Northern Ireland; Karthikeyan Saravanan, Mete Ozay, Samsung R&D Institute UK (SRUK), United Kingdom of Great Britain and Northern Ireland
MLSP-L31.6: FedRD: Reducing Divergences for Generalized Federated Learning via Heterogeneity-aware Parameter Guidance
Kaile Wang, Jiannong Cao, The Hong Kong Polytechnic University, Hong Kong; Yu Yang, The Education University of Hong Kong, Hong Kong; Xiaoyin Li, Mingjin Zhang, The Hong Kong Polytechnic University, Hong Kong
Contacts