Univariate vs Multivariate Time Series Forecasting with Transformers
Lists
Only you see this
Abstract
Multivariate time series forecasting is a challenging problem and a number of Transformer-based long-term time series forecasting models have been developed to tackle it. These models, however, are impeded by the additional information available in multivariate forecasting. In this paper we propose a simple univariate setting as an alternative method for producing multivariate forecasts. The univariate model is trained on each individual dimension of the time series. This single model is then used to forecast each dimension of the multivariate forecast in turn. A comparative study shows that our setting outperforms state-of-the-art Transformers in the multivariate setting in benchmark datasets. To investigate why, we set three hypotheses and verify them via an empirical study, which leads to a criterion for when our univariate setting is likely to lead to better performance and reveals flaws in the current multivariate Transformers for long-term time series forecasting.
BibTeX
@inproceedings{murphy2023univariate,
author = {William Michael John Murphy and Ke Chen},
title = {{Univariate vs Multivariate Time Series Forecasting with Transformers}},
booktitle = {International Conference on Learning Representations},
year = {2023},
url = {https://openreview.net/forum?id=GpW327gxLTF},
}Loading related content...