TY - GEN
T1 - Over-the-Air Computation Empowered Federated Learning
T2 - 98th IEEE Vehicular Technology Conference, VTC 2023-Fall
AU - Zhang, Deyou
AU - Xiao, Ming
AU - Skoglund, Mikael
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - In this paper, we investigate the communication designs of over-the-air computation (AirComp) empowered federated learning (FL) systems considering uplink model aggregation and downlink model dissemination jointly. We first derive an upper bound on the expected difference between the training loss and the optimal loss, which reveals that optimizing the FL performance is equivalent to minimizing the distortion in the received global gradient vector at each edge node. As such, we jointly optimize each edge node transmit and receive equalization coefficients along with the edge server forwarding matrix to minimize the maximum gradient distortion across all edge nodes. We further utilize the MNIST dataset to evaluate the performance of the considered FL system in the context of the handwritten digit recognition task. Experiment results show that deploying multiple antennas at the edge server significantly reduces the distortion in the received global gradient vector, leading to a notable improvement in recognition accuracy compared to the single antenna case.
AB - In this paper, we investigate the communication designs of over-the-air computation (AirComp) empowered federated learning (FL) systems considering uplink model aggregation and downlink model dissemination jointly. We first derive an upper bound on the expected difference between the training loss and the optimal loss, which reveals that optimizing the FL performance is equivalent to minimizing the distortion in the received global gradient vector at each edge node. As such, we jointly optimize each edge node transmit and receive equalization coefficients along with the edge server forwarding matrix to minimize the maximum gradient distortion across all edge nodes. We further utilize the MNIST dataset to evaluate the performance of the considered FL system in the context of the handwritten digit recognition task. Experiment results show that deploying multiple antennas at the edge server significantly reduces the distortion in the received global gradient vector, leading to a notable improvement in recognition accuracy compared to the single antenna case.
KW - Federated learning
KW - joint uplink-downlink design
KW - over-the-air computation
UR - https://www.scopus.com/pages/publications/85181165722
U2 - 10.1109/VTC2023-Fall60731.2023.10333467
DO - 10.1109/VTC2023-Fall60731.2023.10333467
M3 - 会议稿件
AN - SCOPUS:85181165722
T3 - IEEE Vehicular Technology Conference
BT - 2023 IEEE 98th Vehicular Technology Conference, VTC 2023-Fall - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 10 October 2023 through 13 October 2023
ER -