paper-with-me

Papers

Cross-Frequency Time Series Meta-Forecasting

2023-02-04 · Mike Van Ness, Huibin Shen, Hao Wang, Xiaoyong Jin, Danielle C. Maddix, Karthick Gopalswamy

Meta-forecasting is a newly emerging field which combines meta-learning and time series forecasting. The goal of meta-forecasting is to train over a collection of source time series and generalize to new time series one-at-a-time. Previous approaches in meta-forecasting achieve competitive performance, but with the restriction of training a separate model for each sampling frequency. In this work, we investigate meta-forecasting over different sampling frequencies, and introduce a new model, the Continuous Frequency Adapter (CFA), specifically designed to learn frequency-invariant representations. We find that CFA greatly improves performance when generalizing to unseen frequencies, providing a first step towards forecasting over larger multi-frequency datasets.

📄 PDF Abstract BibTeX arXiv:2302.02077

Code (0)

등록된 구현이 없습니다.

Tasks

Meta-LearningTime SeriesTime Series AnalysisTime Series Forecasting

Methods 이 논문이 사용한 방법론

Adapter 설명 없음

Similar Papers 제목 키워드 기반

Metadata Matters for Time Series: Informative Forecasting with Transformers

2024-10-04 · Jiaxiang Dong, Haixu Wu, Yuxuan Wang, Li Zhang 외

Time series forecasting is prevalent in extensive real-world applications, such as financial analysis and energy planning. Previous studies primarily focus on time series modality, endeavoring to capture the intricate va…

Financial AnalysisTime SeriesTime Series Forecasting

Meta-Forecasting by combining Global Deep Representations with Local Adaptation

2021-11-05 · Riccardo Grazzi, Valentin Flunkert, David Salinas, Tim Januschowski 외

While classical time series forecasting considers individual time series in isolation, recent advances based on deep learning showed that jointly learning from a large pool of related time series can boost the forecastin…

Meta-LearningTime SeriesTime Series AnalysisTime Series Forecasting

ROSE: Register Assisted General Time Series Forecasting with Decomposed Frequency Learning

2024-05-24 · Yihang Wang, Yuying Qiu, Peng Chen, Kai Zhao 외

With the increasing collection of time series data from various domains, there arises a strong demand for general time series forecasting models pre-trained on a large number of time-series datasets to support a variety …

Time SeriesTime Series Forecasting

Tailored Forecasting from Short Time Series via Meta-learning

2025-01-27 · Declan A. Norton, Edward Ott, Andrew Pomerance, Brian Hunt 외

Machine learning (ML) models can be effective for forecasting the dynamics of unknown systems from time-series data, but they often require large amounts of data and struggle to generalize across systems with varying dyn…

Meta-LearningTime Series

Automatic Forecasting via Meta-Learning

2021-09-29 · Mustafa Abdallah, Ryan Rossi, Kanak Mahadik, Sungchul Kim 외

In this work, we develop techniques for fast automatic selection of the best forecasting model for a new unseen time-series dataset, without having to first train (or evaluate) all the models on the new time-series data …

Meta-LearningTime SeriesTime Series AnalysisTime Series Forecasting