Connecting the dots: multivariate time series forecasting with graph neural networks

Zonghan Wu, Shirui Pan, Guodong Long, Jing Jiang, Xiaojun Chang, Chengqi Zhang

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

Abstract

Modeling multivariate time series has long been a subject that has attracted researchers from a diverse range of fields including economics, finance, and traffic. A basic assumption behind multivariate
time series forecasting is that its variables depend on one another but, upon looking closely, it is fair to say that existing methods fail to fully exploit latent spatial dependencies between pairs of variables.
In recent years, meanwhile, graph neural networks (GNNs) have shown high capability in handling relational dependencies. GNNs require well-defined graph structures for information propagation
which means they cannot be applied directly for multivariate time series where the dependencies are not known in advance. In this paper, we propose a general graph neural network framework designed specifically for multivariate time series data. Our approach automatically extracts the uni-directed relations among variables through a graph learning module, into which external knowledge like variable attributes can be easily integrated. A novel mix-hop propagation layer and a dilated inception layer are further proposed to capture the spatial and temporal dependencies within the time series. The graph learning, graph convolution, and temporal convolution modules are jointly learned in an end-to-end framework. Experimental results show that our proposed model outperforms the state-of-the-art baseline methods on 3 of 4 benchmark datasets
and achieves on-par performance with other approaches on two traffic datasets which provide extra structural information.
Original languageEnglish
Title of host publicationProceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
EditorsJiliang Tang, B. Aditya Prakash
Place of PublicationNew York NY USA
PublisherAssociation for Computing Machinery (ACM)
Pages753–763
Number of pages11
ISBN (Electronic)9781450379984
DOIs
Publication statusPublished - Aug 2020
EventACM International Conference on Knowledge Discovery and Data Mining 2020 - Virtual, Online, United States of America
Duration: 23 Aug 202027 Aug 2020
Conference number: 26th
https://dl.acm.org/doi/proceedings/10.1145/3394486 (Proceedings)
https://www.kdd.org/kdd2020/ (Website)

Conference

ConferenceACM International Conference on Knowledge Discovery and Data Mining 2020
Abbreviated titleKDD 2020
Country/TerritoryUnited States of America
CityVirtual, Online
Period23/08/2027/08/20
Internet address

Keywords

  • Graph neural networks
  • graph structure learning
  • multivariate time series forecasting
  • spatial-temporal graphs

Cite this