ASA: Adaptive Smart Agent Federated Learning via Device-Aware Clustering for Heterogeneous IoT
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914331499692032 |
|---|---|
| author | Salimi, Ali Izadi, Saadat Ahmadi, Mahmood Malazi, Hadi Tabatabaee |
| author_facet | Salimi, Ali Izadi, Saadat Ahmadi, Mahmood Malazi, Hadi Tabatabaee |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_14391 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ASA: Adaptive Smart Agent Federated Learning via Device-Aware Clustering for Heterogeneous IoT Salimi, Ali Izadi, Saadat Ahmadi, Mahmood Malazi, Hadi Tabatabaee Networking and Internet Architecture 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. |
| title | ASA: Adaptive Smart Agent Federated Learning via Device-Aware Clustering for Heterogeneous IoT |
| topic | Networking and Internet Architecture |
| url | https://arxiv.org/abs/2602.14391 |