Semi-Federated Learning for Edge Intelligence with Imperfect SIC

W Ni, J Zheng, YC Eldar, C You… - ICASSP 2023-2023 …, 2023 - ieeexplore.ieee.org
… , we propose a new semi-federated learning (SemiFL) framework … consider imperfect
successive interference cancellation (SIC… of imperfect SIC on the communication and learning

Semi-federated learning: Convergence analysis and optimization of a hybrid learning framework

J Zheng, W Ni, H Tian, D Gündüz… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
… , we propose a semi-federated learning (SemiFL) paradigm to leverage the computing
capabilities of both the BS and devices for a hybrid implementation of centralized learning (CL) …

Semi-Federated Learning for Connected Intelligence With Computing-Heterogeneous Devices

J Han, W Ni, L Li - IEEE Internet of Things Journal, 2024 - ieeexplore.ieee.org
… ] considered the case of imperfect channel state information … [17] proposed a semi-federated
learning paradigm where data … interference cancellation (SIC), where the individual NOMA …

Balancing accuracy and integrity for reconfigurable intelligent surface-aided over-the-air federated learning

J Zheng, H Tian, W Ni, W Ni… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
… when the number of receive antennas is small or moderate under imperfect CSI. … SIC is
carried out. Considering the effectiveness of the model recovery, we take the convention of SIC

[引用][C] Convergence Analysis and Latency Minimization for Semi-Federated Learning in Massive IoT Networks......................

H Li, A Emami, KDR Assis, A Vafeas, R Yang… - ieeexplore.ieee.org
… Based Multiple Relayed NOMA System With Imperfect CSI and SIC Errors . . . . . . . . . . . . . . . .
. . . . … Joint Optimization of Resource Allocation and SIC Ordering in Energy-Harvesting Relay-…

Network for Distributed Intelligence: A Survey and Future Perspectives

C Campolo, A Iera, A Molinaro - IEEE Access, 2023 - ieeexplore.ieee.org
imperfect CSI and under fast-varying channel environments. Deep Reinforcement Learning
can … is proposed for Federated Learning under communication limitations and imperfect CSI. …