FedPA: A Performance-Based Approach for Resource-Optimized and Imbalance-Resilient Federated Learning

Federated Learning (FL) has emerged as a pivotal framework for privacy-preserving collaborative model training, especially in domains such as healthcare, telecommunication, finance where data sensitivity is paramount. While traditional FL techniques like Federated Averaging (FedAvg) and Federated Stochastic Gradient Descent (FedSGD) offer simplicity and efficiency, they often struggle in heterogeneous data environments due to equal treatment of all client contributions, regardless of quality. This leads to degraded global model performance, high communication overhead, and slow convergence, particularly under non-IID data and client variability. To address these limitations, we propose Performance-Based Federated Partial Averaging (FedPA), a novel aggregation method that selectively incorporates updates from high-performing clients based on local accuracy and F1-score thresholds. Unlike FedAvg, FedPA excludes low-performing updates from global aggregation, while still allowing underperforming clients to receive global model updates for progressive learning. This approach mitigates the adverse effects of noisy contributions, accelerates convergence, and reduces communication overhead. We validate FedPA using the MNIST dataset under a simulated non-IID federated setting. Experimental results show that FedPA achieves competitive accuracy and F1 scores with significantly fewer communication rounds compared to FedAvg. Additionally, FedPA demonstrates robustness to client-side class imbalance and data heterogeneity, outperforming baselines in fairness, convergence stability, and communication efficiency. Our findings suggest that performance-aware aggregation strategies like FedPA hold strong potential for scalable and equitable deployment of FL systems in real-world, data-sensitive applications. Especially in 5G wireless networks, where optimized resource allocation and communication efficiency are essential, FedPA effectively aligns performance-driven aggregation with resource constraints, paving the way for intelligent and adaptive FL deployment across edge-cloud infrastructures.