Personalized Federated Learning-Driven Beamforming Optimization for Integrated Sensing and Communication Systems

Abstract

In this paper, we propose an Expectation-Maximization-based (EM) Personalized Federated Learning (PFL) framework for multi-objective optimization (MOO) in Integrated Sensing and Communication (ISAC) systems. In contrast to standard federated learning (FL) methods that handle all clients uniformly, the proposed approach enables each base station (BS) to adaptively determine its aggregation weight with the EM algorithm. Specifically, an EM posterior is computed at each BS to quantify the relative suitability between the global and each local model, based on the losses of models on their respective datasets. The proposed method is especially valuable in scenarios with competing communication and sensing objectives, as it enables BSs to dynamically adapt to application-specific trade-offs. To assess the effectiveness of the proposed approach, we conduct simulation studies under both objective-wise homogeneous and heterogeneous conditions. The results demonstrate that our approach outperforms existing PFL baselines, such as FedPer and pFedMe, achieving faster convergence and better multi-objective performance.