Adaptive graph recurrent network for multivariate time series imputation

Yakun CHEN, Zihao LI, Chao YANG, Xianzhi WANG, Guodong LONG, Guandong XU

Research output: Chapter in Book/Report/Conference proceedingChapters

Abstract

Multivariate time series inherently involve missing values for various reasons, such as incomplete data entry, equipment malfunctions, and package loss in data transmission. Filling missing values is important for ensuring the performance of subsequent analysis tasks. Most existing methods for missing value imputation neglect inter-variable relations in time series. Although graph-based methods can capture such relations, the design of graph structures commonly requires domain knowledge. In this paper, we propose an adaptive graph recurrent network (AGRN) that combines graph and recurrent neural networks for multivariate time series imputation. Our model can learn variable- and time-specific dependencies effectively without extra information such as domain knowledge. Our extensive experiments on real-world datasets demonstrate our model’s superior performance to state-of-the-art methods. Copyright © 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Original languageEnglish
Title of host publicationNeural information processing: 29th International Conference, ICONIP 2022, Virtual Event, November 22–26, 2022, proceedings, part V
EditorsMohammad TANVEER, Sonali AGARWAL, Seiichi OZAWA, Asif EKBAL, Adam JATOWT
Place of PublicationSingapore
PublisherSpringer
Pages64-73
ISBN (Electronic)9789819916429
ISBN (Print)9789819916412
DOIs
Publication statusPublished - 2023

Citation

Chen, Y., Li, Z., Yang, C., Wang, X., Long, G., & Xu, G. (2023). Adaptive graph recurrent network for multivariate time series imputation. In M. Tanveer, S. Agarwal, S. Ozawa, A. Ekbal, & A. Jatowt (Eds.), Neural information processing: 29th International Conference, ICONIP 2022, Virtual Event, November 22–26, 2022, proceedings, part V (pp. 64-73). Springer. https://doi.org/10.1007/978-981-99-1642-9_6

Keywords

  • Graph neural network
  • Multivariate time series imputation
  • Spatio-temporal graph learning

Fingerprint

Dive into the research topics of 'Adaptive graph recurrent network for multivariate time series imputation'. Together they form a unique fingerprint.