DynamicFL: Federated Learning with Dynamic Communication Resource Allocation

TL;DR

DynamicFL is a federated learning framework that optimizes communication resource allocation based on data heterogeneity, significantly improving model accuracy and bridging the gap between FedSGD and FedAvg methods.

Contribution

It introduces a novel resource allocation strategy that adapts to data heterogeneity, enhancing federated learning performance under communication constraints.

Findings

Up to 10% increase in model accuracy over state-of-the-art methods.

Effectively balances communication costs and model performance.

Bridges the gap between FedSGD and FedAvg methods.

Abstract

Federated Learning (FL) is a collaborative machine learning framework that allows multiple users to train models utilizing their local data in a distributed manner. However, considerable statistical heterogeneity in local data across devices often leads to suboptimal model performance compared with independently and identically distributed (IID) data scenarios. In this paper, we introduce DynamicFL, a new FL framework that investigates the trade-offs between global model performance and communication costs for two widely adopted FL methods: Federated Stochastic Gradient Descent (FedSGD) and Federated Averaging (FedAvg). Our approach allocates diverse communication resources to clients based on their data statistical heterogeneity, considering communication resource constraints, and attains substantial performance enhancements compared to uniform communication resource allocation. Notably, our method bridges the gap between FedSGD and FedAvg, providing a flexible framework leveraging communication heterogeneity to address statistical heterogeneity in FL. Through extensive experiments, we demonstrate that DynamicFL surpasses current state-of-the-art methods with up to a 10% increase in model accuracy, demonstrating its adaptability and effectiveness in tackling data statistical heterogeneity challenges.