MagiNet: Mask-Aware Graph Imputation Network for Incomplete Traffic Data
This addresses missing data issues in Intelligent Transportation Systems for traffic analysis, representing a strong specific gain but incremental over existing imputation methods.
The paper tackles the problem of missing traffic data imputation by proposing MagiNet, which avoids pre-filling missing values and reduces over-smoothing, resulting in an average improvement of 4.31% in RMSE and 3.72% in MAPE over state-of-the-art methods on five real-world datasets.
Due to detector malfunctions and communication failures, missing data is ubiquitous during the collection of traffic data. Therefore, it is of vital importance to impute the missing values to facilitate data analysis and decision-making for Intelligent Transportation System (ITS). However, existing imputation methods generally perform zero pre-filling techniques to initialize missing values, introducing inevitable noises. Moreover, we observe prevalent over-smoothing interpolations, falling short in revealing the intrinsic spatio-temporal correlations of incomplete traffic data. To this end, we propose Mask-Aware Graph imputation Network: MagiNet. Our method designs an adaptive mask spatio-temporal encoder to learn the latent representations of incomplete data, eliminating the reliance on pre-filling missing values. Furthermore, we devise a spatio-temporal decoder that stacks multiple blocks to capture the inherent spatial and temporal dependencies within incomplete traffic data, alleviating over-smoothing imputation. Extensive experiments demonstrate that our method outperforms state-of-the-art imputation methods on five real-world traffic datasets, yielding an average improvement of 4.31% in RMSE and 3.72% in MAPE.