TRAIL: Trust-Aware Client Scheduling for Semi-Decentralized Federated Learning

TL;DR

TRAIL is a trust-aware client scheduling mechanism for semi-decentralized federated learning that improves training efficiency and accuracy by selectively involving clients based on their estimated states and contributions.

Contribution

The paper introduces an adaptive hidden semi-Markov model and a greedy scheduling algorithm to effectively select clients in semi-decentralized FL, addressing dynamic client states.

Findings

Achieves 8.7% higher test accuracy compared to baselines.

Reduces training loss by 15.3%.

Effectively models client states with semi-Markov approach.

Abstract

Due to the sensitivity of data, Federated Learning (FL) is employed to enable distributed machine learning while safeguarding data privacy and accommodating the requirements of various devices. However, in the context of semi-decentralized FL, clients' communication and training states are dynamic. This variability arises from local training fluctuations, heterogeneous data distributions, and intermittent client participation. Most existing studies primarily focus on stable client states, neglecting the dynamic challenges inherent in real-world scenarios. To tackle this issue, we propose a TRust-Aware clIent scheduLing mechanism called TRAIL, which assesses client states and contributions, enhancing model training efficiency through selective client participation. We focus on a semi-decentralized FL framework where edge servers and clients train a shared global model using unreliable intra-cluster model aggregation and inter-cluster model consensus. First, we propose an adaptive hidden semi-Markov model to estimate clients' communication states and contributions. Next, we address a client-server association optimization problem to minimize global training loss. Using convergence analysis, we propose a greedy client scheduling algorithm. Finally, our experiments conducted on real-world datasets demonstrate that TRAIL outperforms state-of-the-art baselines, achieving an improvement of 8.7% in test accuracy and a reduction of 15.3% in training loss.