Reliable Traffic State Estimation via Vertical Federated Learning

Traffic state estimation (TSE) is critical in underpinning the route planning of intelligent transportation systems (ITS). In light of vertical split traffic data might be from various entities, such as municipal authority (MA) and multiple mobility providers (MPs), vertical federated learning (VFL)-based TSE is proposed to resolve the vertical data privacy issue. However, due to discrepancies in data collection and missing data imputation technologies of MPs, the data quality of MPs regarding the same road segment might vary. To this end, we propose a reliable VFL-based TSE framework, including data provider selection and VFL model training. Concretely, given the high-dimension nature of traffic data, the MA will train a tiny mutual information (MI) model for data provider selection. After that, the MA will split the well-trained MI model into sub-models and top models and deploy them on MPs and MA, respectively, so as to preserve the nature of VFL. Eventually, upon MI models, the most representative MP of each road segment is selected for a reliable VFL model. Numerical simulation on real-world datasets shows that our framework augments the performance of traffic flow and traffic density by 11.23% and 21.15% in comparison with the baseline without data provider selection.