AGSTN: Learning attention-adjusted graph spatio-temporal networks for short-term urban sensor value forecasting

Yi Ju Lu, Cheng Te Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Forecasting spatio-temporal correlated time series of sensor values is crucial in urban applications, such as air pollution alert, biking resource management, and intelligent transportation systems. While recent advances exploit graph neural networks (GNN) to better learn spatial and temporal dependencies between sensors, they cannot model time-evolving spatio-temporal correlation (STC) between sensors, and require pre-defined graphs, which are neither always available nor totally reliable, and target at only a specific type of sensor data at one time. Moreover, since the form of time-series fluctuation is varied across sensors, a model needs to learn fluctuation modulation. To tackle these issues, in this work, we propose a novel GNN-based model, Attention-adjusted Graph Spatio-Temporal Network (AGSTN). In AGSTN, multi-graph convolution with sequential learning is developed to learn time-evolving STC. Fluctuation modulation is realized by a proposed attention adjustment mechanism. Experiments on three sensor data, air quality, bike demand, and traffic flow, exhibit that AGSTN outperforms the state-of-the-art methods.

Original languageEnglish
Title of host publicationProceedings - 20th IEEE International Conference on Data Mining, ICDM 2020
EditorsClaudia Plant, Haixun Wang, Alfredo Cuzzocrea, Carlo Zaniolo, Xindong Wu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1148-1153
Number of pages6
ISBN (Electronic)9781728183169
DOIs
Publication statusPublished - 2020 Nov
Event20th IEEE International Conference on Data Mining, ICDM 2020 - Virtual, Sorrento, Italy
Duration: 2020 Nov 172020 Nov 20

Publication series

NameProceedings - IEEE International Conference on Data Mining, ICDM
Volume2020-November
ISSN (Print)1550-4786

Conference

Conference20th IEEE International Conference on Data Mining, ICDM 2020
CountryItaly
CityVirtual, Sorrento
Period20-11-1720-11-20

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Fingerprint Dive into the research topics of 'AGSTN: Learning attention-adjusted graph spatio-temporal networks for short-term urban sensor value forecasting'. Together they form a unique fingerprint.

Cite this