Omni-Dimensional Frequency Learner for General Time Series Analysis

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Xianing, Chen, Hanting, Hu, Hailin
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929427022086144
author Chen, Xianing
Chen, Hanting
Hu, Hailin
author_facet Chen, Xianing
Chen, Hanting
Hu, Hailin
contents Frequency domain representation of time series feature offers a concise representation for handling real-world time series data with inherent complexity and dynamic nature. However, current frequency-based methods with complex operations still fall short of state-of-the-art time domain methods for general time series analysis. In this work, we present Omni-Dimensional Frequency Learner (ODFL) model based on a in depth analysis among all the three aspects of the spectrum feature: channel redundancy property among the frequency dimension, the sparse and un-salient frequency energy distribution among the frequency dimension, and the semantic diversity among the variable dimension. Technically, our method is composed of a semantic-adaptive global filter with attention to the un-salient frequency bands and partial operation among the channel dimension. Empirical results show that ODFL achieves consistent state-of-the-art in five mainstream time series analysis tasks, including short- and long-term forecasting, imputation, classification, and anomaly detection, offering a promising foundation for time series analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2407_10419
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Omni-Dimensional Frequency Learner for General Time Series Analysis
Chen, Xianing
Chen, Hanting
Hu, Hailin
Computer Vision and Pattern Recognition
Machine Learning
Frequency domain representation of time series feature offers a concise representation for handling real-world time series data with inherent complexity and dynamic nature. However, current frequency-based methods with complex operations still fall short of state-of-the-art time domain methods for general time series analysis. In this work, we present Omni-Dimensional Frequency Learner (ODFL) model based on a in depth analysis among all the three aspects of the spectrum feature: channel redundancy property among the frequency dimension, the sparse and un-salient frequency energy distribution among the frequency dimension, and the semantic diversity among the variable dimension. Technically, our method is composed of a semantic-adaptive global filter with attention to the un-salient frequency bands and partial operation among the channel dimension. Empirical results show that ODFL achieves consistent state-of-the-art in five mainstream time series analysis tasks, including short- and long-term forecasting, imputation, classification, and anomaly detection, offering a promising foundation for time series analysis.
title Omni-Dimensional Frequency Learner for General Time Series Analysis
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2407.10419