FedGPO: Heterogeneity-Aware Global Parameter Optimization for Efficient Federated Learning
This addresses efficiency and convergence issues in federated learning for mobile devices, representing an incremental improvement with specific gains.
The paper tackles the challenge of energy-efficient federated learning deployment under system/data heterogeneity and runtime variance, proposing FedGPO to optimize global parameters, resulting in 2.4 times faster model convergence and 3.6 times higher energy efficiency compared to baselines.
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.