VARS-FL: Validation-Aligned Client Selection for Non-IID Federated Learning in IoT Systems

2026-05-07

AI Summary

This work addresses the slow convergence, training instability, and misalignment between local and global objectives in conventional federated learning under non-IID IoT settings, primarily caused by stateless client selection. To overcome these limitations, the authors propose VARS-FL, a novel framework that quantifies client contributions through the reduction in server-side validation loss. VARS-FL introduces a history-aware reputation score by integrating sliding-window averaging with logarithmically scaled participation rates, thereby balancing exploration and exploitation without modifying local training or aggregation procedures. Evaluated on the Edge-IIoTset dataset, VARS-FL consistently outperforms FedAvg, Oort, and Power-of-Choice in terms of accuracy, F1-Macro, and loss, reducing the number of communication rounds required to reach 80% accuracy by up to 36%.

Abstract

Federated learning (FL) systems typically employ stateless client selection, treating each communication round independently and ignoring accumulated evidence of client contribution quality. Under non-IID data, this leads to slow convergence and unstable training, particularly when selection relies on local proxies (e.g., training loss) that are misaligned with the global optimization objective. These challenges are especially pronounced in Internet of Things (IoT) and Industrial IoT (IIoT) environments, where data is highly heterogeneous and distributed across devices observing different traffic patterns. In this paper, we propose VARS-FL (Validation-Aligned Reputation Scoring for Federated Learning), a client selection framework that quantifies each client's contribution using the reduction in server-side validation loss induced by its update. These per-round signals are aggregated into a Reputation score that combines a sliding-window average of recent contributions with a logarithmically scaled participation term, enabling robust exploration-exploitation selection. VARS-FL requires no changes to local training or aggregation and remains fully compatible with standard FedAvg. We evaluate VARS-FL on a 15-class non-IID IoT intrusion detection task using the Edge-IIoTset dataset, with 100 clients across multiple seeds, and compare it against FedAvg, Oort, and Power-of-Choice. VARS-FL consistently improves accuracy, F1-Macro, and loss, while accelerating convergence (up to 36% fewer rounds to reach 80% accuracy). These results demonstrate that validation-aligned, history-aware client selection provides a more reliable and efficient training process for federated learning in heterogeneous IoT environments.

Problem

• Federated Learning
• Non-IID
• Client Selection
• IoT
• Convergence

Innovation

• client selection
• validation-aligned
• reputation scoring
• non-IID federated learning
• IoT