Data-Similarity Based Integrated Federated and Centralized Learning for 6G Communications

It is commonly believed that 6G will be established on ubiquitous artificial intelligence (AI). Federated learning is recognized as one of the vital solutions for 6G intelligent applications due to its distributed AI structure and privacy preservation nature. In this paper, we consider an integrated federated and centralized learning network that consists of multiple users and a server for acquiring perceived data from mobile devices. The data similarity rule is adopted at users, where the received data offloaded from devices is either retained at users for distributed training or relayed to server for centralized training, and thus the server also aggregates local models from users. By optimizing bandwidth resource allocation and the number of communication rounds, we formulate an optimization problem with the goal of energy consumption minimization under the constraints of model loss and communication delay. Simulation results show that the proposed scheme not only improves model performance but also reduces energy consumption.