TY - GEN
T1 - AGSTN
T2 - 20th IEEE International Conference on Data Mining, ICDM 2020
AU - Lu, Yi Ju
AU - Li, Cheng Te
N1 - Funding Information:
This work is supported by Ministry of Science and Technology (MOST) of Taiwan under grants 109-2636-E-006-017 (MOST Young Scholar Fellowship) and 109-2221-E-006-173, and also by Academia Sinica under grant AS-TP-107-M05.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/11
Y1 - 2020/11
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85100896818&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85100896818&partnerID=8YFLogxK
U2 - 10.1109/ICDM50108.2020.00140
DO - 10.1109/ICDM50108.2020.00140
M3 - Conference contribution
AN - SCOPUS:85100896818
T3 - Proceedings - IEEE International Conference on Data Mining, ICDM
SP - 1148
EP - 1153
BT - Proceedings - 20th IEEE International Conference on Data Mining, ICDM 2020
A2 - Plant, Claudia
A2 - Wang, Haixun
A2 - Cuzzocrea, Alfredo
A2 - Zaniolo, Carlo
A2 - Wu, Xindong
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 17 November 2020 through 20 November 2020
ER -
