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

TL;DR

VARS-FL introduces a validation-based client selection method for federated learning in IoT systems, improving convergence speed and accuracy under non-IID data conditions.

Contribution

It proposes a novel reputation scoring framework that aligns client selection with global validation loss reduction without altering local training or aggregation.

Findings

VARS-FL outperforms FedAvg, Oort, and Power-of-Choice in accuracy and convergence speed.

It reduces the number of rounds to reach 80% accuracy by up to 36%.

VARS-FL is effective in highly heterogeneous IoT environments.

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.