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

Yi Ju Lu, Cheng Te Li

研究成果: Conference contribution

摘要

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.

原文English
主出版物標題Proceedings - 20th IEEE International Conference on Data Mining, ICDM 2020
編輯Claudia Plant, Haixun Wang, Alfredo Cuzzocrea, Carlo Zaniolo, Xindong Wu
發行者Institute of Electrical and Electronics Engineers Inc.
頁面1148-1153
頁數6
ISBN(電子)9781728183169
DOIs
出版狀態Published - 2020 十一月
事件20th IEEE International Conference on Data Mining, ICDM 2020 - Virtual, Sorrento, Italy
持續時間: 2020 十一月 172020 十一月 20

出版系列

名字Proceedings - IEEE International Conference on Data Mining, ICDM
2020-November
ISSN(列印)1550-4786

Conference

Conference20th IEEE International Conference on Data Mining, ICDM 2020
國家/地區Italy
城市Virtual, Sorrento
期間20-11-1720-11-20

All Science Journal Classification (ASJC) codes

  • 工程 (全部)

指紋

深入研究「AGSTN: Learning attention-adjusted graph spatio-temporal networks for short-term urban sensor value forecasting」主題。共同形成了獨特的指紋。

引用此