Efficient Data Labeling and Optimal Device Scheduling in HWNs Using Clustered Federated Semi-Supervised Learning

TL;DR

This paper introduces CFSL, a semi-supervised federated learning framework for hierarchical wireless networks that improves data labeling efficiency, reduces resource consumption, and accelerates convergence in non-IID data scenarios.

Contribution

The paper proposes a novel CFSL framework combining specialized models, ensemble schemes, and device selection strategies tailored for HWNs, addressing practical unlabeled data challenges.

Findings

CFSL outperforms existing methods in labeling and testing accuracy.

Achieves up to 51% energy savings in resource consumption.

Enhances convergence speed and reduces processing times.

Abstract

Clustered Federated Multi-task Learning (CFL) has emerged as a promising technique to address statistical challenges, particularly with non-independent and identically distributed (non-IID) data across users. However, existing CFL studies entirely rely on the impractical assumption that devices possess access to accurate ground-truth labels. This assumption becomes problematic in hierarchical wireless networks (HWNs), with vast unlabeled data and dual-level model aggregation, slowing convergence speeds, extending processing times, and increasing resource consumption. To this end, we propose Clustered Federated Semi-Supervised Learning (CFSL), a novel framework tailored for realistic scenarios in HWNs. We leverage specialized models from device clustering and present two prediction model schemes: the best-performing specialized model and the weighted-averaging ensemble model. The former assigns the most suitable specialized model to label unlabeled data, while the latter unifies specialized models to capture broader data distributions. CFSL introduces two novel prediction time schemes, split-based and stopping-based, for accurate labeling timing, and two device selection strategies, greedy and round-robin. Extensive testing validates CFSL's superiority in labeling/testing accuracy and resource efficiency, achieving up to 51% energy savings.