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 |