Edge Federated Learning

Edge Federated Learning For Autonomous Vehicle Perception

S. Wang, Y. Hong, R. Wang, Q. Hao, Y.-C. Wu, and D. W. K. Ng, “Edge federated learning via unit-modulus over-the-air computation,” IEEE Transactions on Communications, vol. 70, no. 5, pp. 3141-3156, May 2021.

Edge federated learning (FL) is an emerging paradigm that trains a global parametric model from distributed datasets based on wireless communications. We propose a unit-modulus over-the-air computation (UMAirComp) framework to facilitate efficient edge federated learning, which simultaneously uploads local model parameters and updates global model parameters via analog beamforming. The proposed framework avoids sophisticated baseband signal processing, leading to low communication delays and implementation costs. We demonstrate the implementation of UMAirComp-FL in a vehicle-to-everything autonomous driving perception platform.