time-series-11

Traffic Data Imputation

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in traffic-data-imputation-11

Trend

Dataset

Best Model

Actions

METR-LA Point Missing

PEMS-BAY Point Missing

Libraries

i

Use these libraries to find traffic-data-imputation-11 models and implementations

xinychen/transdim

4 papers 1,136

Datasets

METR-LA Point Missing

PEMS-BAY Point Missing

Subtasks

No subtasks available.

Most implemented papers

BRITS: Bidirectional Recurrent Imputation for Time Series

Lei Li, Hao Zhou, Wei Cao, Jian Li, Yitan Li•Mon Apr 30 2018

BRITS is a novel method based on recurrent neural networks for missing value imputation in time series data that directly learns the missing values in a bidirectional recurrent dynamical system, without any specific assumption.

797

Content

WenjieDu/PyPOTS

2 papers 648

0

Paper Graph

Scalable low-rank tensor learning for spatiotemporal traffic data imputation

Lijun Sun, N. Saunier, Xinyu Chen, Yixian Chen•Thu Aug 06 2020

A scalable tensor learning model based on the existing framework of Low-Rank Tensor Completion, which is well-suited for spatiotemporal traffic data that is characterized by multidimensional structure of location, and can achieve competitive accuracy with a significantly lower computational cost.

77 0

Paper Graph

Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks

Andrea Cini, Ivan Marisca, C. Alippi•Fri Jul 30 2021

A novel graph neural network architecture is introduced, named GRIN, which aims at reconstructing missing data in the different channels of a multivariate time series by learning spatio-temporal representations through message passing and outperforms state-of-the-art methods in the imputation task on relevant real-world benchmarks.

157 0

Paper Graph

Learning to Reconstruct Missing Data from Spatiotemporal Graphs with Sparse Observations

Andrea Cini, Ivan Marisca, C. Alippi•Wed May 25 2022

This paper proposes a novel class of attention-based architectures that, given a set of highly sparse discrete observations, learn a representation for points in time and space by exploiting a spatiotemporal propagation architecture aligned with the imputation task.

109 0

Paper Graph

Traffic Data Imputation Using Deep Convolutional Neural Networks

O. Benkraouda, Bilal Thonnam Thodi, H. Yeo, M. Menéndez, S. Jabari•Mon Jan 20 2020

The results show that with probe vehicle penetration levels as low as 5%, the proposed estimation method can provide a sound reconstruction of macroscopic traffic speeds and reproduce realistic shockwave patterns, implying applicability in a variety of traffic conditions.

35 0

Paper Graph

A Nonconvex Low-Rank Tensor Completion Model for Spatiotemporal Traffic Data Imputation

Lijun Sun, Xinyu Chen, Jin-Ming Yang•Sun Mar 22 2020

This paper formulate the missing data imputation problem in spatiotemporal traffic data in a low-rank tensor completion (LRTC) framework and define a novel truncated nuclear norm (TNN) on traffic tensors of location $\times$day$\times $time of day.

170 0

Paper Graph

Low-Rank Autoregressive Tensor Completion for Spatiotemporal Traffic Data Imputation

Lijun Sun, N. Saunier, Xinyu Chen, Mengying Lei•Thu Apr 29 2021

A low-rank autoregressive tensor completion (LATC) framework is proposed by introducing temporal variation as a new regularization term into the completion of a third-order tensor structure to better capture the global consistency of traffic data, such as the inherent seasonality and day-to-day similarity.

143 0

Paper Graph

Truncated tensor Schatten p-norm based approach for spatiotemporal traffic data imputation with complicated missing patterns

Tong Nie, Guoyang Qin, Jian Sun•Wed May 18 2022

An innovative nonconvex truncated Schatten p-norm for tensors (TSpN) is defined to approximate tensor rank and impute missing spatiotemporal traffic data under the LRTC framework and derives the global optimal solutions by integrating the alternating direction method of multipliers with generalized soft-thresholding (GST).

68 0

Paper Graph

Adding a benchmark result helps the community track progress.