CCP-federated deep learning based on user trust chain in social IoV

【Author】 Zhao, Peng-Cheng; Huang, Yuan-Hao; Zhang, De-Xin; Xing, Ling; Wu, Hong-Hai; Gao, Jian-Ping

【Source】WIRELESS NETWORKS

【影响因子】2.701

【Abstract】Federated learning is widely used in the context of wireless networks to protect sensitive user data. However, centralized federated learning encounters some issues when applied to the Social Internet of Vehicles, specifically low communication efficiency and high computational cost. In order to alleviate communication bottlenecks and protect vehicle user data privacy, we herein propose the Conditional Choice Probability-Federated Deep Learning algorithm based on user trust chain. This algorithm introduces inter-user trust elements to characterize the vehicle connection network from a vehicle-user relationship perspective. It computes the node conditional choice trust probability based on the single-way trust atomic chain and circular chain of user nodes. Local model interactions are then performed to complete the decentralized federated deep learning framework. Experiments are conducted to verify the robustness of the proposed algorithm's conditional choice probability estimation and confirm that decentralized federated deep learning is effective.

【Keywords】Social Internet of Vehicles (SIoV); Conditional Choice Probability (CCP); Trust chain; Privacy protection; Federated deep learning

【发表时间】

【收录时间】2022-01-09

【文献类型】期刊

【主题类别】

区块链技术--