7 papers · 1 filter
Privacy Enhancement in Over-the-Air Federated Learning via Adaptive Receive Scaling
Faeze Moradi Kalarde, Ben Liang, Min Dong +2
In Federated Learning (FL) with over-the-air aggregation, the quality of the signal received at the server critically depends on the receive scaling factors. While a larger scaling…
Robust Segmented Analog Broadcast Design to Accelerate Wireless Federated Learning
Chong Zhang, Ben Liang, Min Dong +2
We consider downlink broadcast design for federated learning (FL) in a wireless network with imperfect channel state information (CSI). Aiming to reduce transmission latency, we pr…
SegOTA: Accelerating Over-the-Air Federated Learning with Segmented Transmission
Chong Zhang, Min Dong, Ben Liang +2
Federated learning (FL) with over-the-air computation efficiently utilizes the communication resources, but it can still experience significant latency when each device transmits a…
Improving Wireless Federated Learning via Joint Downlink-Uplink Beamforming over Analog Transmission
Chong Zhang, Min Dong, Ben Liang +2
Federated learning (FL) over wireless networks using analog transmission can efficiently utilize the communication resource but is susceptible to errors caused by noisy wireless li…
Power-Efficient Over-the-Air Aggregation with Receive Beamforming for Federated Learning
Faeze Moradi Kalarde, Min Dong, Ben Liang +2
This paper studies power-efficient uplink transmission design for federated learning (FL) that employs over-the-air analog aggregation and multi-antenna beamforming at the server.…
Uplink Over-the-Air Aggregation for Multi-Model Wireless Federated Learning
Chong Zhang, Min Dong, Ben Liang +2
We propose an uplink over-the-air aggregation (OAA) method for wireless federated learning (FL) that simultaneously trains multiple models. To maximize the multi-model training con…