Over-the-Air Federated Learning via Weighted Aggregation
It addresses performance degradation in federated learning due to wireless channel variability and device heterogeneity, offering a practical solution for distributed machine learning in communication-constrained environments.
This paper tackles the problem of federated learning over wireless networks by proposing a scheme with adaptive weighted aggregation to mitigate channel condition impacts without needing channel state information, achieving accuracy improvements of 15% over CSIT-based methods and 30% over non-CSIT methods.
This paper introduces a new federated learning scheme that leverages over-the-air computation. A novel feature of this scheme is the proposal to employ adaptive weights during aggregation, a facet treated as predefined in other over-the-air schemes. This can mitigate the impact of wireless channel conditions on learning performance, without needing channel state information at transmitter side (CSIT). We provide a mathematical methodology to derive the convergence bound for the proposed scheme in the context of computational heterogeneity and general loss functions, supplemented with design insights. Accordingly, we propose aggregation cost metrics and efficient algorithms to find optimized weights for the aggregation. Finally, through numerical experiments, we validate the effectiveness of the proposed scheme. Even with the challenges posed by channel conditions and device heterogeneity, the proposed scheme surpasses other over-the-air strategies by an accuracy improvement of 15% over the scheme using CSIT and 30% compared to the one without CSIT.