Contract-based Incentive Mechanism for Blockchain-enabled Federated Learning in Vehicle Edge Computing

Vehicular edge computing (VEC) has been introduced to bring powerful in-proximity computing solutions to vehicles. VEC is able to boost the development of vehicular networks by handling computing tasks and accommodating artificial intelligence (AI). To fulfill the requirements of low latency and security in realizing AI for vehicular networks, and fully utilize the vehicles' capabilities on sensing and computing, federated learning (FL) in VEC emerges as a potential solution. However, privacy protection, data security and information asymmetry issues pose challenges on efficiently and securely motivating more vehicles to participate in FL. Thus, this paper proposes a contract-based incentive mechanism for blockchain-enabled FL, which employs contract theory to establish an optimal contract design between VEC servers and vehicles. We present the necessary and sufficient conditions to obtain an optimal contract and analyze the simplification of the constraints. The simulation results show that our proposed method is effective in providing incentives and outperforms other benchmark schemes.