FedGreen: Federated Learning with Fine-Grained Gradient Compression for Green Mobile Edge Computing

TL;DR

FedGreen introduces a fine-grained gradient compression method in federated learning for mobile edge computing, significantly reducing energy consumption while maintaining high accuracy.

Contribution

The paper proposes FedGreen, a novel approach that applies fine-grained gradient compression in federated learning to optimize energy efficiency in green MEC environments.

Findings

Reduces at least 32% of energy consumption at 80% accuracy

Effectively balances learning accuracy and energy efficiency

Demonstrates superior performance over baseline schemes

Abstract

Federated learning (FL) enables devices in mobile edge computing (MEC) to collaboratively train a shared model without uploading the local data. Gradient compression may be applied to FL to alleviate the communication overheads but current FL with gradient compression still faces great challenges. To deploy green MEC, we propose FedGreen, which enhances the original FL with fine-grained gradient compression to efficiently control the total energy consumption of the devices. Specifically, we introduce the relevant operations including device-side gradient reduction and server-side element-wise aggregation to facilitate the gradient compression in FL. According to a public dataset, we investigate the contributions of the compressed local gradients with respect to different compression ratios. After that, we formulate and tackle a learning accuracy-energy efficiency tradeoff problem where the optimal compression ratio and computing frequency are derived for each device. Experiments results demonstrate that given the 80% test accuracy requirement, compared with the baseline schemes, FedGreen reduces at least 32% of the total energy consumption of the devices.