Private Federated Learning with Dynamic Power Control via Non-Coherent Over-the-Air Computation
This work addresses privacy and performance issues in federated learning for edge computing applications, but appears incremental as it builds on existing over-the-air computation methods.
The paper tackles the problem of preserving model weight privacy and improving performance in Federated Learning by proposing a scheme using dynamic power control with non-coherent over-the-air computation, which mitigates synchronization errors, channel fading, and noise, and includes a theoretical convergence proof.
To further preserve model weight privacy and improve model performance in Federated Learning (FL), FL via Over-the-Air Computation (AirComp) scheme based on dynamic power control is proposed. The edge devices (EDs) transmit the signs of local stochastic gradients by activating two adjacent orthogonal frequency division multi-plexing (OFDM) subcarriers, and majority votes (MVs) at the edge server (ES) are obtained by exploiting the energy accumulation on the subcarriers. Then, we propose a dynamic power control algorithm to further offset the biased aggregation of the MV aggregation values. We show that the whole scheme can mitigate the impact of the time synchronization error, channel fading and noise. The theoretical convergence proof of the scheme is re-derived.