Clipped Uniform Quantizers for Communication-Efficient Federated Learning

This paper introduces an approach to employ clipped uniform quantization in federated learning settings, aiming to enhance model efficiency by reducing communication overhead without compromising accuracy. We explore the implications of symmetric clipping and uniform quantization on model performance, highlighting the utility of stochastic quantization to mitigate quantization artifacts and improve model robustness. Through extensive simulations on the MNIST dataset, our results demonstrate that the proposed method achieves near full-precision performance while ensuring substantial communication savings. Specifically, our approach facilitates efficient weight averaging based on quantization errors, effectively balancing the trade-off between communication efficiency and model accuracy. The comparative analysis with conventional quantization methods further confirms the superiority of our technique.