Federated Learning via Lattice Joint Source-Channel Coding
This work addresses efficient and reliable model aggregation in federated learning for distributed systems, representing an incremental improvement over existing over-the-air strategies.
The paper tackles the problem of enabling over-the-air computation in federated learning via digital communications without channel state information, using a lattice-based joint source-channel coding scheme to quantize and aggregate model parameters, resulting in a framework that markedly surpasses other over-the-air FL strategies in numerical experiments.
This paper introduces a universal federated learning framework that enables over-the-air computation via digital communications, using a new joint source-channel coding scheme. Without relying on channel state information at devices, this scheme employs lattice codes to both quantize model parameters and exploit interference from the devices. A novel two-layer receiver structure at the server is designed to reliably decode an integer combination of the quantized model parameters as a lattice point for the purpose of aggregation. Numerical experiments validate the effectiveness of the proposed scheme. Even with the challenges posed by channel conditions and device heterogeneity, the proposed scheme markedly surpasses other over-the-air FL strategies.