One-Shot Federated Learning With Lightweight Intermediate Models in Wireless Sensor Network Setting

Abstract

One-shot federated learning (FL) completes model training and aggregation in a single communication round, significantly reducing communication costs compared to traditional FL. This approach is particularly suitable for resource-constrained environments such as wireless sensor networks (WSNs). However, existing solutions face significant challenges in aggregation owing to model heterogeneity, where clients adopt architectures of varying depth, width, and computational capacity. To address this issue, we propose a one-shot FL method named FedLIM, which employs a lightweight intermediate model for efficient knowledge transfer and global model aggregation. The Fisher information matrix (FIM) is incorporated to guide the model aggregation process and improve its robustness. Although FedLIM completes global training and aggregation in a single communication round, an optional personalized model adjustment step is introduced afterward. This step only involves server-to-client distribution without additional aggregation. Experimental results on three datasets demonstrate that FedLIM achieves superior global model accuracy compared to existing one-shot FL methods, particularly in highly heterogeneous environments. Moreover, the accuracy of local models is further enhanced through this optional refinement step.