# Dynamic Spatiotemporal Graph Convolutional Neural Networks for Traffic Data Imputation with Complex Missing Patterns

arXiv: https://arxiv.org/abs/2109.08357 · HTML: https://mlsanity.com/paper/2109.08357/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 48 references that are in the map.
- First posted on arXiv 17 Sep 2021.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting](https://mlsanity.com/paper/1709.04875/) (2017)
- [Graph WaveNet for Deep Spatial-Temporal Graph Modeling](https://mlsanity.com/paper/1906.00121/) (2019)
- [GMAN: A Graph Multi-Attention Network for Traffic Prediction](https://mlsanity.com/paper/1911.08415/) (2019)
- [GAIN: Missing Data Imputation using Generative Adversarial Nets](https://mlsanity.com/paper/1806.02920/) (2018)
- [Inductive Graph Neural Networks for Spatiotemporal Kriging](https://mlsanity.com/paper/2006.07527/) (2020)
- [Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction](https://mlsanity.com/paper/1901.08518/) (2019)
- [Missing Data Imputation with Adversarially-trained Graph Convolutional Networks](https://mlsanity.com/paper/1905.01907/) (2019)
- [Bayesian Temporal Factorization for Multidimensional Time Series Prediction](https://mlsanity.com/paper/1910.06366/) (2019)
- [Bidirectional Recurrent Neural Networks as Generative Models - Reconstructing Gaps in Time Series](https://mlsanity.com/paper/1504.01575/) (2015)
- [Graph Markov Network for Traffic Forecasting with Missing Data](https://mlsanity.com/paper/1912.05457/) (2019)
- [NetTraj: A Network-based Vehicle Trajectory Prediction Model with Directional Representation and Spatiotemporal Attention Mechanisms](https://mlsanity.com/paper/2106.11175/) (2021)
- [Traffic Data Imputation using Deep Convolutional Neural Networks](https://mlsanity.com/paper/2002.04406/) (2020)
- [A convolution recurrent autoencoder for spatio-temporal missing data imputation](https://mlsanity.com/paper/1904.12413/) (2019)

## Built on by (most cited first, 9 of 9)

- [A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection](https://mlsanity.com/paper/2307.03759/) (2023)
- [Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observations](https://mlsanity.com/paper/2205.13479/) (2022)
- [ImputeFormer: Low Rankness-Induced Transformers for Generalizable Spatiotemporal Imputation](https://mlsanity.com/paper/2312.01728/) (2023)
- [Joint Demand Prediction for Multimodal Systems: A Multi-task Multi-relational Spatiotemporal Graph Neural Network Approach](https://mlsanity.com/paper/2112.08078/) (2021)
- [Towards better traffic volume estimation: Jointly addressing the underdetermination and nonequilibrium problems with correlation-adaptive GNNs](https://mlsanity.com/paper/2303.05660/) (2023)
- [Spatiotemporal Implicit Neural Representation as a Generalized Traffic Data Learner](https://mlsanity.com/paper/2405.03185/) (2024)
- [Joint Estimation and Prediction of City-wide Delivery Demand: A Large Language Model Empowered Graph-based Learning Approach](https://mlsanity.com/paper/2408.17258/) (2024)
- [Large-Scale Traffic Data Imputation with Spatiotemporal Semantic Understanding](https://mlsanity.com/paper/2301.11691/) (2023)
- [Learning Time-Varying Graphs from Incomplete Graph Signals](https://mlsanity.com/paper/2510.17903/) (2025)

## Abstract (arXiv)

Missing data is an inevitable and ubiquitous problem for traffic data collection in intelligent transportation systems. Despite extensive research regarding traffic data imputation, there still exist two limitations to be addressed: first, existing approaches fail to capture the complex spatiotemporal dependencies in traffic data, especially the dynamic spatial dependencies evolving with time; second, prior studies mainly focus on randomly missing patterns while other more complex missing scenarios are less discussed. To fill these research gaps, we propose a novel deep learning framework called Dynamic Spatiotemporal Graph Convolutional Neural Networks (DSTGCN) to impute missing traffic data. The model combines the recurrent architecture with graph-based convolutions to model the spatiotemporal dependencies. Moreover, we introduce a graph structure estimation technique to model the dynamic spatial dependencies from real-time traffic information and road network structure. Extensive experiments based on two public traffic speed datasets are conducted to compare our proposed model with state-of-the-art deep learning approaches in four types of missing patterns. The results show that our proposed model outperforms existing deep learning models in all kinds of missing scenarios and the graph structure estimation technique contributes to the model performance. We further compare our proposed model with a tensor factorization model and find distinct behaviors across different model families under different training schemes and data availability.