Coded Over-the-Air Computation for Model Aggregation in Federated Learning
Naifu Zhang, Meixia Tao, Jia Wang, Shuo Shao
Abstract
This letter introduces a new coded transmission design for model aggregation in federated learning (FL) over Gaussian multiple access channels (MAC), named coded over-the-air computation (codedAirComp). It enjoys the optimality of analog AirComp-based uncoded transmission for fast model aggregation, but also leverages the traditional source-channel separation principle for more practical uses. Specifically, the proposed codedAirComp employs stochastic uniform quantization for local gradient compression and nested lattice coding for channel transmission. Compared with the traditional coding scheme, the proposed scheme significantly reduces the model aggregation distortion and improves the overall learning accuracy.