Publication Date: 2/22/2021
Event: AAAI 2021 – 35th AAAI Conference on Artificial Intelligence
Reference: pp. 1-9, 2021, Virtual Conference
Authors: Yinjun Wu, University of Pennsylvania; Jingchao Ni, NEC Laboratories America, Inc.; Wei Cheng, NEC Laboratories America, Inc.; Bo Zong, NEC Laboratories America, Inc.; Dongjin Song, University of Connecticut; Zhengzhang Chen, NEC Laboratories America, Inc.; Yanchi Liu,, NEC Laboratories America, Inc.; Xuchao Zhang, NEC Laboratories America, Inc.; Haifeng Chen, NEC Laboratories America, Inc.; Susan Davidson, University of Pennsylvania
Abstract: Forecasting on sparse multivariate time series (MTS) aims to model the predictors of future values of time series given their incomplete past, which is important for many emerging applications. However, most existing methods process MTS’s individually, and do not leverage the dynamic distributions underlying the MTS’s, leading to sub-optimal results when the sparsity is high. To address this challenge, we propose a novel generative model, which tracks the transition of latent clusters, instead of isolated feature representations, to achieve robust modeling. It is characterized by a newly designed dynamic Gaussian mixture distribution, which captures the dynamics of clustering structures, and is used for emitting time series. The generative model is parameterized by neural networks. A structured inference network is also designed for enabling inductive analysis. A gating mechanism is further introduced to dynamically tune the Gaussian mixture distributions. Extensive experimental results on a variety of real-life datasets demonstrate the effectiveness of our method.