FedGPO: Heterogeneity-Aware Global Parameter Optimization for Efficient Federated Learning

TL;DR

FedGPO is a reinforcement learning-based method that optimizes global parameters in federated learning, significantly improving convergence speed and energy efficiency amid system and data heterogeneity.

Contribution

This paper introduces FedGPO, a novel reinforcement learning approach that adaptively tunes global parameters for efficient federated learning under heterogeneity.

Findings

FedGPO reduces convergence time by 2.4 times.

FedGPO achieves 3.6 times higher energy efficiency.

It effectively adapts to system and data heterogeneity.

Abstract

Federated learning (FL) has emerged as a solution to deal with the risk of privacy leaks in machine learning training. This approach allows a variety of mobile devices to collaboratively train a machine learning model without sharing the raw on-device training data with the cloud. However, efficient edge deployment of FL is challenging because of the system/data heterogeneity and runtime variance. This paper optimizes the energy-efficiency of FL use cases while guaranteeing model convergence, by accounting for the aforementioned challenges. We propose FedGPO based on a reinforcement learning, which learns how to identify optimal global parameters (B, E, K) for each FL aggregation round adapting to the system/data heterogeneity and stochastic runtime variance. In our experiments, FedGPO improves the model convergence time by 2.4 times, and achieves 3.6 times higher energy efficiency over the baseline settings, respectively.