Full Bayesian Significance Testing for Neural Networks in Traffic Forecasting

Due to the complex and dynamic traffic contexts, the interpretability and uncertainty of traffic fore- casting have gained increasing attention. Signifi- cance testing is a powerful tool in statistics used to determine whether a hypothesis is valid, facilitating the identification of pivotal features that predomi- nantly contribute to the true relationship. However, existing works mainly regard traffic forecasting as a deterministic problem, making it challenging to perform effective significance testing. To fill this gap, we propose to conduct Full Bayesian Signifi- cance Testing for Neural Networks in Traffic Fore- casting, namely ST-nFBST. A Bayesian neural net- work is utilized to capture the complicated traffic relationships through an optimization function re- solved in the context of aleatoric uncertainty and epistemic uncertainty. Thereupon, ST-nFBST can achieve the significance testing by means of a del- icate grad-based evidence value, further capturing the inherent traffic schema for better spatiotempo- ral modeling. Extensive experiments are conducted on METR-LA and PEMS-BAY to verify the advan- tages of our method in terms of uncertainty analysis and significance testing, helping the interpretability and promotion of traffic forecasting.