TY - GEN
T1 - Network of tensor time series
AU - Jing, Baoyu
AU - Tong, Hanghang
AU - Zhu, Yada
N1 - Funding Information:
920th Century Reanalysis V3 data provided by the NOAA/OAR/ESRL PSL, Boulder, Colorado, USA, from their Web site https://psl.noaa.gov/data/gridded/data.20thC_ ReanV3.html 10Support for the Twentieth Century Reanalysis Project version 3 dataset is provided by the U.S. Department of Energy, Office of Science Biological and Environmental Research (BER), by the National Oceanic and Atmospheric Administration Climate Program Office, and by the NOAA Physical Sciences Laboratory.
Funding Information:
This work is supported by National Science Foundation under grant No. 1947135, by Agriculture and Food Research Initiative (AFRI) grant no. 2020-67021-32799/project accession no.1024178 from the USDA National Institute of Food and Agriculture, and IBM-ILLINOIS Center for Cognitive Computing Systems Research (C3SR) - a research collaboration as part of the IBM AI Horizons Network. The content of the information in this document does not necessarily reflect the position or the policy of the Government, and no official endorsement should be inferred. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation here on.
Publisher Copyright:
© 2021 ACM.
PY - 2021/4/19
Y1 - 2021/4/19
N2 - Co-evolving time series appears in a multitude of applications such as environmental monitoring, financial analysis, and smart transportation. This paper aims to address the following challenges, including (C1) how to incorporate explicit relationship networks of the time series; (C2) how to model the implicit relationship of the temporal dynamics. We propose a novel model called Network of Tensor Time Series (NeT3), which is comprised of two modules, including Tensor Graph Convolutional Network (TGCN) and Tensor Recurrent Neural Network (TRNN). TGCN tackles the first challenge by generalizing Graph Convolutional Network (GCN) for flat graphs to tensor graphs, which captures the synergy between multiple graphs associated with the tensors. TRNN leverages tensor decomposition to model the implicit relationships among co-evolving time series. The experimental results on five real-world datasets demonstrate the efficacy of the proposed method.
AB - Co-evolving time series appears in a multitude of applications such as environmental monitoring, financial analysis, and smart transportation. This paper aims to address the following challenges, including (C1) how to incorporate explicit relationship networks of the time series; (C2) how to model the implicit relationship of the temporal dynamics. We propose a novel model called Network of Tensor Time Series (NeT3), which is comprised of two modules, including Tensor Graph Convolutional Network (TGCN) and Tensor Recurrent Neural Network (TRNN). TGCN tackles the first challenge by generalizing Graph Convolutional Network (GCN) for flat graphs to tensor graphs, which captures the synergy between multiple graphs associated with the tensors. TRNN leverages tensor decomposition to model the implicit relationships among co-evolving time series. The experimental results on five real-world datasets demonstrate the efficacy of the proposed method.
KW - Co-evolving Time Series
KW - Network of Tensor Time Series
KW - Tensor Graph Convolutional Network
KW - Tensor Recurrent Neural Network
UR - http://www.scopus.com/inward/record.url?scp=85102540131&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85102540131&partnerID=8YFLogxK
U2 - 10.1145/3442381.3449969
DO - 10.1145/3442381.3449969
M3 - Conference contribution
AN - SCOPUS:85102540131
T3 - The Web Conference 2021 - Proceedings of the World Wide Web Conference, WWW 2021
SP - 2425
EP - 2437
BT - The Web Conference 2021 - Proceedings of the World Wide Web Conference, WWW 2021
PB - Association for Computing Machinery, Inc
T2 - 2021 World Wide Web Conference, WWW 2021
Y2 - 19 April 2021 through 23 April 2021
ER -