FusAD: Time-Frequency Fusion with Adaptive Denoising for General Time Series Analysis

TL;DR

FusAD introduces an adaptive time-frequency fusion framework with denoising for robust, multi-task time series analysis across diverse applications, outperforming existing models in accuracy and efficiency.

Contribution

The paper presents FusAD, a novel unified framework combining adaptive time-frequency fusion and denoising for versatile, multi-task time series analysis, addressing limitations of task-specific models.

Findings

FusAD outperforms state-of-the-art models on classification benchmarks.

FusAD effectively handles noisy and complex time series data.

The framework demonstrates high efficiency and scalability across tasks.

Abstract

Time series analysis plays a vital role in fields such as finance, healthcare, industry, and meteorology, underpinning key tasks including classification, forecasting, and anomaly detection. Although deep learning models have achieved remarkable progress in these areas in recent years, constructing an efficient, multi-task compatible, and generalizable unified framework for time series analysis remains a significant challenge. Existing approaches are often tailored to single tasks or specific data types, making it difficult to simultaneously handle multi-task modeling and effectively integrate information across diverse time series types. Moreover, real-world data are often affected by noise, complex frequency components, and multi-scale dynamic patterns, which further complicate robust feature extraction and analysis. To ameliorate these challenges, we propose FusAD, a unified analysis framework designed for diverse time series tasks. FusAD features an adaptive time-frequency fusion mechanism, integrating both Fourier and Wavelet transforms to efficiently capture global-local and multi-scale dynamic features. With an adaptive denoising mechanism, FusAD automatically senses and filters various types of noise, highlighting crucial sequence variations and enabling robust feature extraction in complex environments. In addition, the framework integrates a general information fusion and decoding structure, combined with masked pre-training, to promote efficient learning and transfer of multi-granularity representations. Extensive experiments demonstrate that FusAD consistently outperforms state-of-the-art models on mainstream time series benchmarks for classification, forecasting, and anomaly detection tasks, while maintaining high efficiency and scalability. Code is available at https://github.com/zhangda1018/FusAD.