Performance Evaluation of Data Imputation Methods for Graph Deep Learning-Based Traffic Prediction

We present five approaches for interpolating missing data in real-world traffic datasets using basic, statistical, and generative model methods. The effectiveness of these approaches is evaluated using graph deep learning models, and the results show that imputing missing data improves the performance of traffic prediction models, especially when dealing with a higher proportion of missing data. The experiments are conducted on two real-world datasets, METR-LA and PEMS-BAY, to evaluate the proposed methods comprehensively. The results demonstrate that imputing missing data significantly enhances the performance of traffic prediction models, particularly when dealing with a higher proportion of missing data.