Learning Gaussian Mixture Representations for Tensor Time Series Forecasting
This addresses forecasting challenges for multi-source spatio-temporal data in monitoring systems, such as transportation and air pollutants, and is incremental as it builds on existing TTS modeling efforts.
The paper tackles the problem of forecasting tensor time series (TTS) data, which is high-dimensional and complex, by developing a novel framework called GMRL that models heterogeneity in time, location, and source variables, and shows superiority over state-of-the-art baselines on two real-world datasets.
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.