FedDCT: A Dynamic Cross-Tier Federated Learning Framework in Wireless Networks

TL;DR

FedDCT is a novel federated learning framework that dynamically partitions devices and selects them across tiers to improve training efficiency and accuracy in wireless networks.

Contribution

The paper introduces a dynamic tiering and cross-tier device selection strategy to address resource heterogeneity and stragglers in wireless federated learning.

Findings

54.7% reduction in convergence time

1.83% improvement in convergence accuracy

Effective handling of device heterogeneity in wireless environments

Abstract

Federated Learning (FL), as a privacy-preserving machine learning paradigm, trains a global model across devices without exposing local data. However, resource heterogeneity and inevitable stragglers in wireless networks severely impact the efficiency and accuracy of FL training. In this paper, we propose a novel Dynamic Cross-Tier Federated Learning framework (FedDCT). Firstly, we design a dynamic tiering strategy that dynamically partitions devices into different tiers based on their response times and assigns specific timeout thresholds to each tier to reduce single-round training time. Then, we propose a cross-tier device selection algorithm that selects devices that respond quickly and are conducive to model convergence to improve convergence efficiency and accuracy. Experimental results demonstrate that the proposed approach under wireless networks outperforms the baseline approach, with an average reduction of 54.7\% in convergence time and an average improvement of 1.83\% in convergence accuracy.