A Dynamic Contribution Measurement and Incentive Mechanism for Energy-Efficient Federated Learning in 6G

With 5G being commercialized, researchers have turned attention toward the sixth-generation (6G) network with the vision of connecting intelligence in a green energy-efficient manner. Federated learning triggers an upsurge of green intelligent services such as resources orchestration of communication infrastructures, while preserving privacy and communication efficiency. However, designing effective incentives in federated learning is challenging due to the dynamic available clients and the correlation between clients' contributions during the learning process. In this paper, we propose a dynamic incentive and contribution mechanism to improve energy efficiency and training performance of federated learning. The proposed incentive based on Stackelberg game can timely adjust optimal energy consumption with changes in available clients during federated learning. Meanwhile, the contributions of clients in contribution management are formulated based on cooperative game to capture the correlation between tasks, which satisfies the availability, fairness and additivity. The simulation results show that the proposed scheme can significantly motivate high-performance clients to participate in federated learning, then improve the accuracy and energy efficiency of the federated learning model.