부산대학교 도서관

Vehicles on the road generate a large amount of data, which often can be used to train models for destination prediction and traffic flow prediction in intelligent transportation systems (ITS). To break down the information silos and further strengthen privacy protection, we leverage federated learning and differential privacy in this paper. In order to motivate the participation of data owners, we further devise a single-leader multi-follower Stackelberg game incentive mechanism which accounts for the heterogeneous privacy budgets and participation costs of vehicle owners. Due to the lack of prior knowledge, deep reinforcement learning is used to obtain the approximate solution for each player to achieve the Stackelberg equilibrium. Our proposed framework is capable of achieving a solution close to the Nash Equilibrium.