Optimizing Time Series Forecasting Architectures
A Hierarchical Neural Architecture Search Approach
Abstract
The rapid development of time series forecasting research has brought many deep learning-based modules in this field. However, despite the increasing amount of new forecasting architectures, it is still unclear if we have leveraged the full potential of these existing modules within a properly designed architecture. In this work, we propose a novel hierarchical neural architecture search approach for time series forecasting tasks. With the design of a hierarchical search space, we incorporate many architecture types designed for forecasting tasks and allow for the efficient combination of different forecasting architecture modules. Results on long-term-time-series-forecasting tasks show that our approach can search for lightweight high-performing forecasting architectures across different forecasting tasks.
Details
- Organisation(s)
-
L3S Research Centre
Machine Learning Section
- Type
- Article
- Journal
- Transactions on Machine Learning Research
- Volume
- 2025-October
- ISSN
- 2835-8856
- Publication date
- 09.2025
- Publication status
- E-pub ahead of print
- Peer reviewed
- Yes
- ASJC Scopus subject areas
- Computer Vision and Pattern Recognition, Artificial Intelligence
- Electronic version(s)
-
https://openreview.net/forum?id=Ym2wqojm4e (Access:
Open
)
https://doi.org/10.48550/arXiv.2406.05088 (Access: Open )
