Learning Gaussian Mixture Representations for Tensor Time Series Forecasting

Deng，Jiewen1; Deng，Jinliang1,2; Jiang，Renhe1,3; Song，Xuan1,3

2023

1045-0823

IJCAI International Joint Conference on Artificial Intelligence

2023-August

2077-2085

Tensor time series (TTS) data, a generalization of one-dimensional time series on a high-dimensional space, is ubiquitous in real-world scenarios, especially in monitoring systems involving multi-source spatio-temporal data (e.g., transportation demands and air pollutants). Compared to modeling time series or multivariate time series, which has received much attention and achieved tremendous progress in recent years, tensor time series has been paid less effort. Properly coping with the tensor time series is a much more challenging task, due to its high-dimensional and complex inner structure. In this paper, we develop a novel TTS forecasting framework, which seeks to individually model each heterogeneity component implied in the time, the location, and the source variables. We name this framework as GMRL, short for Gaussian Mixture Representation Learning. Experiment results on two real-world TTS datasets verify the superiority of our approach compared with the state-of-the-art baselines. Code and data are published on https://github.com/beginner-sketch/GMRL.

First ; Corresponding

English

2-s2.0-85170365189

Scopus

1.Southern University of Science and Technology,China
2.University of Technology Sydney,Australia
3.The University of Tokyo,Japan

Deng，Jiewen,Deng，Jinliang,Jiang，Renhe,et al. Learning Gaussian Mixture Representations for Tensor Time Series Forecasting[C],2023:2077-2085.