MagiNet: Mask-Aware Graph Imputation Network for Incomplete Traffic Data

TL;DR

MagiNet is a novel graph neural network designed to accurately impute missing traffic data by learning from incomplete data directly, avoiding pre-filling and reducing over-smoothing, thus improving imputation accuracy.

Contribution

The paper introduces MagiNet, a mask-aware graph imputation network that effectively captures spatio-temporal dependencies in incomplete traffic data without relying on zero pre-filling.

Findings

Outperforms state-of-the-art methods on five traffic datasets.

Achieves 4.31% improvement in RMSE.

Achieves 3.72% improvement in MAPE.

Abstract

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.