Back to Search Start Over

Hybrid Variational Autoencoder for Time Series Forecasting

Authors :
Cai, Borui
Yang, Shuiqiao
Gao, Longxiang
Xiang, Yong
Source :
Knowledge-Based Systems. 281 (2023) 111079
Publication Year :
2023

Abstract

Variational autoencoders (VAE) are powerful generative models that learn the latent representations of input data as random variables. Recent studies show that VAE can flexibly learn the complex temporal dynamics of time series and achieve more promising forecasting results than deterministic models. However, a major limitation of existing works is that they fail to jointly learn the local patterns (e.g., seasonality and trend) and temporal dynamics of time series for forecasting. Accordingly, we propose a novel hybrid variational autoencoder (HyVAE) to integrate the learning of local patterns and temporal dynamics by variational inference for time series forecasting. Experimental results on four real-world datasets show that the proposed HyVAE achieves better forecasting results than various counterpart methods, as well as two HyVAE variants that only learn the local patterns or temporal dynamics of time series, respectively.

Details

Database :
arXiv
Journal :
Knowledge-Based Systems. 281 (2023) 111079
Publication Type :
Report
Accession number :
edsarx.2303.07048
Document Type :
Working Paper
Full Text :
https://doi.org/10.1016/j.knosys.2023.111079