Omni-Dimensional Frequency Learner for General Time Series Analysis

TL;DR

The paper introduces the Omni-Dimensional Frequency Learner (ODFL), a novel frequency domain model that outperforms existing methods in various time series analysis tasks by addressing spectral redundancies and semantic diversity.

Contribution

It presents a new frequency domain approach with a semantic-adaptive filter and partial channel operations, advancing beyond prior frequency-based methods.

Findings

Achieves state-of-the-art results in forecasting, imputation, classification, and anomaly detection.

Effectively handles spectral redundancies and semantic diversity.

Provides a promising foundation for future time series analysis.

Abstract

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.