DeepTime: Deep Time-index Meta-learning for Non-stationary Time-series Forecasting

Gerald Woo, Chenghao Liu, Doyen Sahoo, Akshat Kumar, Steven HoiICLR 2023 · OpenReview

Abstract

Advances in I.T. infrastructure has led to the collection of longer sequences of time-series. Such sequences are typically non-stationary, exhibiting distribution shifts over time -- a challenging scenario for the forecasting task, due to the problems of covariate shift, and conditional distribution shift. In this paper, we show that deep time-index models possess strong synergies with a meta-learning formulation of forecasting, displaying significant advantages over existing neural forecasting methods in tackling the problems arising from non-stationarity. These advantages include having a stronger smoothness prior, avoiding the problem of covariate shift, and having better sample efficiency. To this end, we propose DeepTime, a deep time-index model trained via meta-learning. Extensive experiments on real-world datasets in the long sequence time-series forecasting setting demonstrate that our approach achieves competitive results with state-of-the-art methods, and is highly efficient. Code is attached as supplementary material, and will be publicly released.
BibTeX
@inproceedings{woo2023deeptime,
  author = {Gerald Woo and Chenghao Liu and Doyen Sahoo and Akshat Kumar and Steven Hoi},
  title = {{DeepTime: Deep Time-index Meta-learning for Non-stationary Time-series Forecasting}},
  booktitle = {International Conference on Learning Representations},
  year = {2023},
  url = {https://openreview.net/forum?id=13rQhx37o3u},
}

Loading related content...

Figure