# Spatiotemporal Tensor Completion for Improved Urban Traffic Imputation

arXiv: https://arxiv.org/abs/2103.08323 · HTML: https://mlsanity.com/paper/2103.08323/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 51 references that are in the map.
- First posted on arXiv 12 Mar 2021.

## Builds on (most cited first, 11 of 11)

- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Importance Weighted Autoencoders](https://mlsanity.com/paper/1509.00519/) (2015)
- [GAIN: Missing Data Imputation using Generative Adversarial Nets](https://mlsanity.com/paper/1806.02920/) (2018)
- [Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction](https://mlsanity.com/paper/1610.00081/) (2016)
- [GP-VAE: Deep Probabilistic Time Series Imputation](https://mlsanity.com/paper/1907.04155/) (2019)
- [MisGAN: Learning from Incomplete Data with Generative Adversarial Networks](https://mlsanity.com/paper/1902.09599/) (2019)
- [not-MIWAE: Deep Generative Modelling with Missing not at Random Data](https://mlsanity.com/paper/2006.12871/) (2020)
- [Generalized Canonical Polyadic Tensor Decomposition](https://mlsanity.com/paper/1808.07452/) (2018)
- [Tensor Completion for Weakly-dependent Data on Graph for Metro Passenger Flow Prediction](https://mlsanity.com/paper/1912.05693/) (2019)
- [MIWAE: Deep Generative Modelling and Imputation of Incomplete Data](https://mlsanity.com/paper/1812.02633/) (2018)
- [Understanding Urban Dynamics via Context-aware Tensor Factorization with Neighboring Regularization](https://mlsanity.com/paper/1905.00702/) (2019)

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

- [A Novel Approach to Temporal QoS Estimation via Extended Kalman Filter-Incorporated Latent Feature Analysis](https://mlsanity.com/paper/2606.23010/) (2026)
- [FastSTI: A Fast Conditional Pseudo Numerical Diffusion Model for Spatio-temporal Traffic Data Imputation](https://mlsanity.com/paper/2410.15248/) (2024)
- [Spatiotemporal Regularized Tucker Decomposition Approach for Traffic Data Imputation](https://mlsanity.com/paper/2305.06563/) (2023)
- [JULIA: Joint Multi-linear and Nonlinear Identification for Tensor Completion](https://mlsanity.com/paper/2202.00071/) (2022)
- [Spatial-Temporal Attention Model for Traffic State Estimation with Sparse Internet of Vehicles](https://mlsanity.com/paper/2407.08047/) (2024)
- [Exploration of carbonate aggregates in road construction using ultrasonic and artificial intelligence approaches](https://mlsanity.com/paper/2302.05884/) (2023)
- [Latent Tensor Factorization with Nonlinear PID Control for Missing Data Recovery in Non-Intrusive Load Monitoring](https://mlsanity.com/paper/2504.13483/) (2025)
- [Robust Tensor Completion via Gradient Tensor Nulclear L1-L2 Norm for Traffic Data Recovery](https://mlsanity.com/paper/2506.22732/) (2025)
- [A Unified Variational Imputation Framework for Electric Vehicle Charging Data Using Retrieval-Augmented Language Model](https://mlsanity.com/paper/2601.13476/) (2026)

## Abstract (arXiv)

Effective management of urban traffic is important for any smart city initiative. Therefore, the quality of the sensory traffic data is of paramount importance. However, like any sensory data, urban traffic data are prone to imperfections leading to missing measurements. In this paper, we focus on inter-region traffic data completion. We model the inter-region traffic as a spatiotemporal tensor that suffers from missing measurements. To recover the missing data, we propose an enhanced CANDECOMP/PARAFAC (CP) completion approach that considers the urban and temporal aspects of the traffic. To derive the urban characteristics, we divide the area of study into regions. Then, for each region, we compute urban feature vectors inspired from biodiversity which are used to compute the urban similarity matrix. To mine the temporal aspect, we first conduct an entropy analysis to determine the most regular time-series. Then, we conduct a joint Fourier and correlation analysis to compute its periodicity and construct the temporal matrix. Both urban and temporal matrices are fed into a modified CP-completion objective function. To solve this objective, we propose an alternating least square approach that operates on the vectorized version of the inputs. We conduct comprehensive comparative study with two evaluation scenarios. In the first one, we simulate random missing values. In the second scenario, we simulate missing values at a given area and time duration. Our results demonstrate that our approach provides effective recovering performance reaching 26% improvement compared to state-of-art CP approaches and 35% compared to state-of-art generative model-based approaches.