FedDCT: A Dynamic Cross-Tier Federated Learning Framework in Wireless Networks
This work addresses efficiency and accuracy issues in federated learning for wireless networks, representing an incremental improvement with specific gains.
The paper tackles the problem of resource heterogeneity and stragglers in federated learning over wireless networks by proposing FedDCT, a dynamic cross-tier framework, which reduces convergence time by 54.7% and improves accuracy by 1.83% compared to baselines.
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.