Privacy-Preserving Federated Learning for Data Heterogeneity in 6G Mobile Networks

The development of 6G mobile networks will produce many smart Internet of Things devices and data at the network's edge. Advanced AI technology holds the potential to enable 6G mobile networks to collect and analyze this data for innovative applications and intelligent services. However, the inherent privacy constraints and limited communication resources within 6G mobile networks often make direct data transmission to servers undesirable. Federated learning (FL) is seen as a promising approach to address these problems. Yet, integrating FL into 6G mobile networks presents data heterogeneity issues. In this article, we design and propose a privacy-preserving FL scheme in 6 G mobile networks. The core idea of this scheme is to take both dataset size and the discrepancy between local and global category distributions into consideration to compute the weights of different clients and apply threshold Paillier cryptosystem to perform weighted aggregation on client-encrypted data. Security analysis and experimental results demonstrate the advantages of this scheme in guaranteeing privacy preservation and improving training accuracy. Finally, we present some future directions for the integration of FL and 6G mobile networks.