Efficient Prompt Learning for Traffic Forecasting
For traffic forecasting practitioners, this work provides a lightweight method to improve generalization of existing spatio-temporal GNNs, though it is an incremental application of prompt tuning.
Traffic forecasting models suffer from low generalization due to distribution shifts. The proposed SimpleST prompt tuning framework adapts pre-trained spatio-temporal GNNs to new distributions without retraining, achieving superior prediction accuracy and computational efficiency on five real-world datasets.
Accurate traffic prediction is essential for optimizing transportation systems, enhancing resource allocation, and improving overall urban administration. Spatio-temporal graph neural networks (GNNs) have achieved state-of-the-art performance and have been widely used in various spatio-temporal prediction scenarios. However, these prediction methods often exhibit low generalization ability, struggling with distribution shifts caused by spatio-temporal dynamics. To address this challenge, we propose an approach to enhance the generalization and adaptation of spatio-temporal GNNs through efficient prompting. Specifically, we introduce a lightweight and model-agnostic prompt tuning framework for spatio-temporal GNNs, named SimpleST. It facilitates adapting pre-trained spatio-temporal GNNs to novel distributions while keeping the model parameters fixed. This prompt mechanism reduces the overhead and complexity of adaptation, enabling efficient utilization of pre-trained models for out-of-distribution generalization. Extensive experiments conducted on five real-world urban spatio-temporal datasets demonstrate the superiority of our approach in terms of prediction accuracy and computational efficiency.