Technical Program

Note: All times are in Pacific Daylight Time (UTC -7)

H-5: Federated Learning (invited)

Session Type: Virtual
Time: Wednesday, November 2, 08:00 - 09:00
Location: Virtual H
Virtual Session: Attend on Virtual Platform
 
H-5.1: Federated Minimax Optimization: Improved Convergence Analysis and Algorithms
         Pranay Sharma; Carnegie Mellon University
         Rohan Panda; Carnegie Mellon University
         Gauri Joshi; Carnegie Mellon University
         Pramod Varshney; Syracuse University
 
H-5.2: Personalized Federated Recommender Systems with Private and Partially Federated AutoEncoders
         Qi Le; University of Minnesota
         Enmao Diao; Duke University
         Xinran Wang; University of Minnesota
         Ali Anwar; University of Minnesota
         Vahid Tarokh; Duke University
         Jie Ding; University of Minnesota
 
H-5.3: Mixing Distributions without Mixing Examples: Decentralized Learning with Public and Private Data
         Sean Augenstein; Google
 
H-5.4: Joint bandwidth allocation, computation control, and device scheduling for federated learning with energy harvesting devices
         Li Zeng; ShanghaiTech University
         Dingzhu Wen; ShanghaiTech University
         Guangxu Zhu; Shenzhen Research Institute of Big Data
         Changsheng You; Southern University of Science and Technology
         Qimei Chen; Wuhan University
         Yuanming Shi; ShanghaiTech University