mlsanityData to 14 Oct 2026

MNT-TNN: Spatiotemporal Traffic Data Imputation via Compact Multimode Nonlinear Transform-based Tensor Nuclear Norm

arXiv 2503.22955 ↗First posted 29 Mar 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Imputation of random or non-random missing data is a long-standing research topic and a crucial application for Intelligent Transportation Systems (ITS). However, with the advent of modern communication technologies such as Global Satellite Navigation Systems (GNSS), traffic data collection has introduced new challenges in random missing value imputation and increasing demands for spatiotemporal dependency modelings. To address these issues, we propose a novel spatiotemporal traffic imputation method based on a Multimode Nonlinear Transformed Tensor Nuclear Norm (MNT-TNN), which can effectively capture the intrinsic multimode spatiotemporal correlations and low-rankness of the traffic tensor, represented as location × location × time. To solve the nonconvex optimization problem, we design a proximal alternating minimization (PAM) algorithm with theoretical convergence guarantees. We also suggest an Augmented Transform-based Tensor Nuclear Norm Families (ATTNNs) framework to enhance the imputation results of TTNN techniques, especially at very high miss rates. Extensive experiments on real datasets demonstrate that our proposed MNT-TNN and ATTNNs can outperform the compared state-of-the-art imputation methods, completing the benchmark of random missing traffic value imputation.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 58 references that are in the map. First posted on arXiv 29 Mar 2025.

Builds on

20 of 58 references.

References · 20

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
  4. 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 434
  5. 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 338
  6. 2018Tensor Robust Principal Component Analysis with A New Tensor Nuclear Normcited by 112
  7. 2015Exact tensor completion using t-SVDcited by 70
  8. 2014Novel methods for multilinear data completion and de-noising based on tensor-SVDcited by 56
  9. 2023ImputeFormer: Low Rankness-Induced Transformers for Generalizable Spatiotemporal Imputationcited by 50
  10. 2019Framelet Representation of Tensor Nuclear Norm for Third-Order Tensor Completioncited by 37
  11. 2021Low-Rank Autoregressive Tensor Completion for Spatiotemporal Traffic Data Imputationcited by 35
  12. 2015Smooth PARAFAC Decomposition for Tensor Completioncited by 34
8 more
  1. 2020A Nonconvex Low-Rank Tensor Completion Model for Spatiotemporal Traffic Data Imputationcited by 27
  2. 2020Spatio-Temporal Graph Scattering Transformcited by 19
  3. 2022Correlating sparse sensing for large-scale traffic speed estimation: A Laplacian-enhanced low-rank tensor kriging approachcited by 17
  4. 2022Human-instructed Deep Hierarchical Generative Learning for Automated Urban Planningcited by 15
  5. 2021Nonlinear Transform Induced Tensor Nuclear Norm for Tensor Completioncited by 13
  6. 2020Scalable Low-Rank Tensor Learning for Spatiotemporal Traffic Data Imputationcited by 12
  7. 2022Truncated tensor Schatten p-norm based approach for spatiotemporal traffic data imputation with complicated missing patternscited by 11
  8. 2019Robust Tensor Recovery with Fiber Outliers for Traffic Eventscited by 6

Built on by

Not cited yet.