Dependency earning Graph Neural Network for multivariate forecasting

Arth Patel, Abishek Sriramulu, Christoph Bergmeir, Nicolas Fourrier

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review


Multivariate time series forecasting is an important topic in various disciplines. Many deep learning architectures have been proposed for accurate multivariate forecasting. However, most existing models fail to learn the dependencies between different time series. Lately, studies have shown that implementations of Graph Neural Networks in the field of Natural Language, Computer Vision, and Time Series have achieved exceptional performance. In this paper, we propose an attention-based Multivariate Dependency Learning Graph Neural Network, which aims to better learn the dependencies among variables of a multivariate dataset. The attention scores corresponding to each variable complement the construction process of the graph adjacency matrix to model the spatial dependencies. Our experiments on benchmark datasets show that the proposed architecture improves accuracy on different benchmark datasets compared with the state-of-the-art baseline models.

Original languageEnglish
Title of host publication28th International Conference, ICONIP 2021 Sanur, Bali, Indonesia, December 8–12, 2021 Proceedings, Part V
EditorsTeddy Mantoro, Minho Lee, Media Anugerah Ayu, Kok Wai Wong, Achmad Nizar Hidayanto
Place of PublicationCham Switzerland
Number of pages10
ISBN (Electronic)9783030923075
ISBN (Print)9783030923068
Publication statusPublished - 2021
EventInternational Conference on Neural Information Processing 2021 - Online, Bali, Indonesia
Duration: 8 Dec 202112 Dec 2021
Conference number: 28th (Proceedings)

Publication series

NameCommunications in Computer and Information Science
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937


ConferenceInternational Conference on Neural Information Processing 2021
Abbreviated titleICONIP 2021
Internet address


  • Graph learning
  • Graph Neural Networks
  • Multivariate forecasting
  • Time series

Cite this