The Internet of vehicular things (IoVT) is turning into an indubitably evolving area of interest in either industrial or academic domains. The tremendous information exchanging between IoVT devices enable the development of a wide variety of vehicular applications i.e., intelligent transportation systems and autonomous driving system, etc. However, the sensitivity of this information resulted in growing security privacy concerns. Remarkably, federated learning (FL) is a promising paradigm of distributed learning from vehicular data of distinct agents without communicating the raw data among them. FL can appropriately use the computation power of manifold agents to develop efficient and privacy-preserving solutions for IoVT environment. Thus, this study figures out the potential of the FL approach in developing efficient decentralized solutions that consider the security and privacy concerns of the IoVT system. A federated graph convolutional recurrent network (Fed-GCRN) is introduced to learn spatial-temporal information for traffic flows forecasting. The Fed-GCRN introduce an adaptive differential privacy mechanism to realize a better privacy performance tradeoff. Finally, the current challenges related to FL are discussed along with the hopeful future directions that enable the development of more intelligent, secure, and private IoVT applications.