Edge Federated Learning Via Unit-Modulus Over-The-Air Computation

Understand

Edge federated learning (FL) is an emerging paradigm that trains a global parametric model from distributed datasets based on wireless communications.

• This paper proposes 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.
• Training loss bounds of UMAirComp FL systems are derived and two low-complexity large-scale optimization algorithms, termed penalty alternating minimization (PAM) and accelerated gradient projection (AGP), are proposed to minimize the nonconvex nonsmooth loss bound.