Optimizing Time Series Forecasting Architectures

A Hierarchical Neural Architecture Search Approach

verfasst von

Difan Deng, Marius Lindauer

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.

Organisationseinheit(en)

Forschungszentrum L3S
Fachgebiet Maschinelles Lernen

Typ

Artikel

Journal

Transactions on Machine Learning Research

Band

2025-October

ISSN

2835-8856

Publikationsdatum

09.2025

Publikationsstatus

Elektronisch veröffentlicht (E-Pub)

Peer-reviewed

Ja

ASJC Scopus Sachgebiete

Maschinelles Sehen und Mustererkennung, Artificial intelligence

Elektronische Version(en)

https://openreview.net/forum?id=Ym2wqojm4e (Zugang: Offen)
https://doi.org/10.48550/arXiv.2406.05088 (Zugang: Offen)