TY - JOUR
T1 - TMF-GNN
T2 - Temporal matrix factorization-based graph neural network for multivariate time series forecasting with missing values
AU - Kim, Suhyeon
AU - Lee, Taek Ho
AU - Lee, Junghye
N1 - Publisher Copyright:
© 2025 The Authors
PY - 2025/5/25
Y1 - 2025/5/25
N2 - Missing data in multivariate time series (MTS) is a very common issue, often caused by unreliable sensors and data storage or transmission problems. Particularly, such missing data can cause some errors and biases in the MTS forecasting tasks of real-world applications, implying that proper handling of the missing data is essential. Therefore, in this study, we propose a new method for MTS forecasting with missing values, called a temporal matrix factorization-based graph neural network (TMF-GNN), to improve predictive performance outcomes. TMF-GNN basically uses the concept of TMF, which reconstructs partially observed MTS data. We newly present a data-adaptive regularization method for TMF based on graph-based and sequential deep learning algorithms to capture both the variable-wise and time-wise information of MTS data affected by missingness. We demonstrate the feasibility of the proposed method by conducting various experiments on three MTS datasets and show how it outperforms baseline methods. We believe that our study will have an impact on several MTS-related tasks and that it can be a useful alternative for handling missing values in MTS data.
AB - Missing data in multivariate time series (MTS) is a very common issue, often caused by unreliable sensors and data storage or transmission problems. Particularly, such missing data can cause some errors and biases in the MTS forecasting tasks of real-world applications, implying that proper handling of the missing data is essential. Therefore, in this study, we propose a new method for MTS forecasting with missing values, called a temporal matrix factorization-based graph neural network (TMF-GNN), to improve predictive performance outcomes. TMF-GNN basically uses the concept of TMF, which reconstructs partially observed MTS data. We newly present a data-adaptive regularization method for TMF based on graph-based and sequential deep learning algorithms to capture both the variable-wise and time-wise information of MTS data affected by missingness. We demonstrate the feasibility of the proposed method by conducting various experiments on three MTS datasets and show how it outperforms baseline methods. We believe that our study will have an impact on several MTS-related tasks and that it can be a useful alternative for handling missing values in MTS data.
KW - Graph neural network
KW - Missing value
KW - Time series forecasting
UR - http://www.scopus.com/inward/record.url?scp=85219690945&partnerID=8YFLogxK
U2 - 10.1016/j.eswa.2025.127001
DO - 10.1016/j.eswa.2025.127001
M3 - Article
AN - SCOPUS:85219690945
SN - 0957-4174
VL - 275
JO - Expert Systems with Applications
JF - Expert Systems with Applications
M1 - 127001
ER -