Communication-Efficient Federated Learning via Clipped Uniform Quantization
This work addresses communication bottlenecks in federated learning for distributed systems, offering an incremental improvement over existing quantization methods.
The paper tackles communication inefficiency in federated learning by introducing a clipped uniform quantization method, which reduces bandwidth and memory usage for model weight transmission while maintaining competitive accuracy, achieving near-full-precision performance with substantial communication savings.
This paper presents a novel approach to enhance communication efficiency in federated learning through clipped uniform quantization. By leveraging optimal clipping thresholds and client-specific adaptive quantization schemes, the proposed method significantly reduces bandwidth and memory requirements for model weight transmission between clients and the server while maintaining competitive accuracy. We investigate the effects of symmetric clipping and uniform quantization on model performance, emphasizing the role of stochastic quantization in mitigating artifacts and improving robustness. Extensive simulations demonstrate that the method achieves near-full-precision performance with substantial communication savings. Moreover, the proposed approach facilitates efficient weight averaging based on the inverse of the mean squared quantization errors, effectively balancing the trade-off between communication efficiency and model accuracy. Moreover, in contrast to federated averaging, this design obviates the need to disclose client-specific data volumes to the server, thereby enhancing client privacy. Comparative analysis with conventional quantization methods further confirms the efficacy of the proposed scheme.