MTSTI: A multi-task learning framework for spatiotemporal imputation

Yakun CHEN, Kaize SHI, Xianzhi WANG, Guandong XU

Research output: Chapter in Book/Report/Conference proceedingChapters

Abstract

Spatiotemporal data analysis is crucial for various fields of applications, such as transportation, healthcare, and meteorology. Spatiotemporal data collected in the real world often contain missing values due to sensor failures or transmission loss. Therefore, spatiotemporal imputation aims to fill in the missing values by leveraging the underlying spatial and temporal dependencies in the partially observed data. Previous models for spatiotemporal imputation focus solely on the imputation task as a preparatory step for solving the downstream tasks. Instead, we aim to use downstream tasks to reinforce spatiotemporal imputation and further propose a multi-task learning framework, MTSTI, for spatiotemporal imputation. Our proposed framework utilizes a graph neural network to learn spatiotemporal representations via message-passing. The multi-task learning structure, combining spatiotemporal imputation with the forecasting task, provides additional insights that enhance the model’s performance and generality. Our empirical results demonstrate that our proposed framework outperforms state-of-the-art methods in the imputation task on various real-world datasets across different fields. Copyright © 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG.

Original languageEnglish
Title of host publicationAdvanced data mining and applications: 19th International Conference, ADMA 2023, Shenyang, China, August 21–23, 2023, proceedings, part V
EditorsXiaochun YANG, Heru SUHARTANTO, Guoren WANG, Bin WANG, Jing JIANG, Bing LI, Huaijie ZHU, Ningning CUI
Place of PublicationCham
PublisherSpringer
Pages180-194
ISBN (Electronic)9783031466779
ISBN (Print)9783031466762
DOIs
Publication statusPublished - 2023

Citation

Chen, Y., Shi, K., Wang, X., & Xu, G. (2023). MTSTI: A multi-task learning framework for spatiotemporal imputation. In X. Yang, H. Suhartanto, G. Wang, B. Wang, J. Jiang, B. Li, H. Zhu, & N. Cui (Eds.), Advanced data mining and applications: 19th International Conference, ADMA 2023, Shenyang, China, August 21–23, 2023, proceedings, part V (pp. 180-194). Springer. https://doi.org/10.1007/978-3-031-46677-9_13

Keywords

  • Graph Neural Network
  • Multitask learning
  • Spatiotemporal imputation

Fingerprint

Dive into the research topics of 'MTSTI: A multi-task learning framework for spatiotemporal imputation'. Together they form a unique fingerprint.