FedCGAT: A federated demand prediction method for shared bicycles based on contrastive graph attention mechanism

Abstract

Demand prediction for shared bicycles based on historical trip data helps bicycle management organizations plan the scheduling of bicycles. However, the current prediction methods have the following problems: (1) the bicycle trip station data hides the temporal and spatial information, which is crucial for demand prediction, and the traditional methods cannot effectively use that information. (2) each bicycle organization manages its region, and local region data cannot accurately predict the demand of the whole region. Due to the privacy trip data, organizations cannot share raw data directly, which makes it a challenge to achieve federated multi-participant analyses. To address these issues, we propose a federated learning framework for demand prediction of shared bicycles (FedCGAT). Firstly, we propose a spatio-temporal graph neural network based on an attention mechanism for feature modeling of data. Meanwhile, we propose a graph data augmentation method to eliminate noisy data and capture spatial correlations. Then, we construct an auxiliary task based on contrastive learning to assist model training, which can learn the data features fully. Finally, we conducted experiments on two real-world bicycle datasets. The experiments demonstrate that FedCCAT achieves high prediction accuracy while preserving data privacy. Compared to the best-performing baseline model on both datasets, our model achieves reductions in MAPE values of 1.67% and 1.94%, respectively.