Optimizing federated learning with weighted aggregation in aerial and space networks

Federated learning offers a promising solution for overcoming the challenges of networking and data privacy in aerial and space networks by harnessing large-scale private edge data and computing resources from drones, balloons, and satellites. Although existing research has extensively explored optimizing the learning process, improving computing efficiency, and reducing communication overhead, statistical heterogeneity remains a substantial challenge for federated learning optimization. While state-of-the-art algorithms have made progress, they often overlook diversity heterogeneity and fail to significantly improve performance in high-degree label heterogeneity conditions. In this paper, statistical heterogeneity is further dissected into two categories: diversity heterogeneity and label heterogeneity, allowing for a more nuanced analysis. It also emphasizes the importance of addressing both diversity heterogeneity and high-degree label heterogeneity in aerial and space network applications. A theoretical analysis is provided to guide optimization in these two challenging scenarios. To tackle diversity heterogeneity, the WeiAvgCS algorithm is introduced to accelerate federated learning convergence. This algorithm employs weighted aggregation and client selection based on an estimated diversity measure, termed projection , enabling WeiAvgCS to outperform other benchmarks without compromising privacy. For high-degree label heterogeneity, the FedBalance algorithm is proposed, utilizing the label distribution information of each client. A novel metric, termed relative scarcity , is introduced to determine the aggregation weights assigned to clients. During the training process, fully homomorphic encryption is employed to protect clients’ label distributions. Additionally, two communication protocols are designed to facilitate training across different scenarios. Extensive experiments were conducted, demonstrating the effectiveness of WeiAvgCS and FedBalance in addressing the research gaps in diversity heterogeneity and high-degree label heterogeneity. • Statistical heterogeneity was dissected into diversity heterogeneity and label heterogeneity. An analysis of FL applications on ASNs revealed that previous research often overlooked diversity heterogeneity and frequently focused on less heterogeneous label heterogeneity. • A theoretical analysis was conducted to guide the optimization of FL for both diversity heterogeneity and high-degree label heterogeneity. • The WeiAvgCS and FedBalance algorithms were developed to address diversity heterogeneity and high-degree label heterogeneity, respectively. • Extensive experiments were conducted to demonstrate the superiority of WeiAvgCS and FedBalance in various scenarios.