ASA: Adaptive Smart Agent Federated Learning via Device-Aware Clustering for Heterogeneous IoT

TL;DR

ASA introduces an adaptive federated learning framework that clusters IoT devices based on real-time resources, optimizing model training for heterogeneity and significantly reducing communication costs while improving accuracy.

Contribution

The paper presents ASA, a novel device-aware clustering approach for federated learning that dynamically adapts models to device capabilities, enhancing efficiency and fairness in heterogeneous IoT networks.

Findings

Reduces communication burden by up to 50%.

Improves resource utilization by 43%.

Achieves high accuracy on benchmark datasets.

Abstract

Federated learning (FL) has become a promising answer to facilitating privacy-preserving collaborative learning in distributed IoT devices. However, device heterogeneity is a key challenge because IoT networks include devices with very different computational powers, memory availability, and network environments. To this end, we introduce ASA (Adaptive Smart Agent). This new framework clusters devices adaptively based on real-time resource profiles and adapts customized models suited to every cluster's capability. ASA capitalizes on an intelligent agent layer that examines CPU power, available memory, and network environment to categorize devices into three levels: high-performance, mid-tier, and low-capability. Each level is provided with a model tuned to its computational power to ensure inclusive engagement across the network. Experimental evaluation on two benchmark datasets, MNIST and CIFAR-10, proves that ASA decreases communication burden by 43% to 50%, improves resource utilization by 43%, and achieves final model accuracies of 98.89% on MNIST and 85.30% on CIFAR-10. These results highlight ASA's efficacy in enhancing efficiency, scalability, and fairness in heterogeneous FL environments, rendering it a suitable answer for real-world IoT apps.