Accurate future traffic flow prediction is essential for decision-making in travel recommendations and route planning, aiming to reduce congestion and enhance traffic safety. Traditional traffic flow prediction models often face limitations in quality and structure, leading to increased training costs and inefficiencies, due to data scarcity and centralized training modes that compromise data privacy. To address these issues, we propose a model called 2MGTCN, which combines Multi-modal Graph Convolutional Networks (GCN) and Temporal Convolutional Networks (TCN) for Cross-city Traffic Flow Prediction (TFP). Our 2MGTCN model utilizes federated transfer learning (FTL) to transfer the model from the source to the target domain, mitigating data scarcity. It also incorporates GCN and TCN to capture both spatial and temporal information, enhancing cross-city adaptability. Additionally, Grey Relation Analysis (GRA) and Dynamic Time Warping (DTW) methods are applied to capture road relationships, and a Federated Parameter Aggregation based on Spatial Similarity (FPASS) algorithm is proposed for ensuring effective parameter aggregation by considering spatial similarity. Simulation results show that our 2MGTCN algorithm outperforms traditional TFP models in both centralized and distributed training modes, ensuring higher accuracy and better privacy protection.
Federated Transfer Learning for Privacy-Preserved Cross-City Traffic Flow Prediction
IEEE Transactions on Intelligent Transportation Systems ; 26 , 4 ; 4418-4431
2025-04-01
1276916 byte
Article (Journal)
Electronic Resource
English
Cross-city traffic flow prediction federal transfer learning algorithm based on privacy protection
European Patent Office | 2024
|Transfer Learning for Cross-City Traffic Prediction to Solve Data Scarcity
Transportation Research Record | 2024
|Cluster type federated learning-based urban traffic flow prediction method
European Patent Office | 2024
|