DAMR: Dynamic Adjacency Matrix Representation Learning for Multivariate Time Series Imputation
Proceedings of the ACM on Management of Data · 13.06.2023 · 1 (2) · 1-25
DOI: 10.1145/3589333 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the ACM on Management of Data, online erschienen am 20.06.2023. Verfasst von Xiaobin Ren und 5 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: Marsden Fund Council from Government Funding.
Abstract (Originalsprache)
Missing data imputation for location-based sensor data has attracted much attention in recent years. The state-of-the-art imputation methods based on graph neural networks have a priori assumption that the spatial correlations between sensor locations are static. However, real-world data sets often exhibit dynamic spatial correlations. This paper proposes a novel approach to capturing the dynamics of spatial correlations between geographical locations as a composition of the constant, long-term trends and periodic patterns. To this end, we design a new method called Dynamic Adjacency Matrix Representation (DAMR) that extracts various dynamic patterns of spatial correlations and represents them as adjacency matrices. The adjacency matrices are then aggregated and fed into a well-designed graph representation learning layer for predicting the missing values. Through extensive experiments on six real-world data sets, we demonstrate that DAMR reduces the MAE by up to 19.4% compared with the state-of-the-art methods for the missing value imputation task
Förderung
- Marsden Fund Council from Government Funding
Zitieren
APA
Ren, X., Zhao, K., Riddle, P. J., Taskova, K., Pan, Q., & Li, L. (2023). DAMR: Dynamic Adjacency Matrix Representation Learning for Multivariate Time Series Imputation. Proceedings of the ACM on Management of Data, 1(2), 1-25. https://doi.org/10.1145/3589333
Vancouver
Ren X, Zhao K, Riddle PJ, Taskova K, Pan Q, Li L. DAMR: Dynamic Adjacency Matrix Representation Learning for Multivariate Time Series Imputation. Proceedings of the ACM on Management of Data. 2023;1(2):1-25. doi:10.1145/3589333
BibTeX
@article{Ren2023,
author = {Ren, Xiaobin and Zhao, Kaiqi and Riddle, Patricia J. and Taskova, Katerina and Pan, Qingyi and Li, Lianyan},
title = {DAMR: Dynamic Adjacency Matrix Representation Learning for Multivariate Time Series Imputation},
journal = {Proceedings of the ACM on Management of Data},
year = {2023},
volume = {1},
number = {2},
pages = {1--25},
doi = {10.1145/3589333}
}
EUVIMED