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

2025-12-15

AI Summary

To address key challenges in time-series analysis—including poor multi-task compatibility, weak generalization across heterogeneous data types, and difficulty in robust feature extraction under noise—this paper proposes the first unified framework supporting classification, forecasting, and anomaly detection. Methodologically, it introduces an adaptive time-frequency fusion mechanism (integrating Fourier and wavelet transforms) coupled with a noise-aware adaptive denoising module to enable multi-scale dynamic modeling and enhancement of critical temporal changes. Additionally, it incorporates masked pretraining and a multi-granularity information fusion decoder to improve representation universality. Evaluated on mainstream benchmarks, the framework consistently outperforms state-of-the-art methods across all three tasks, achieving significant performance gains while maintaining high computational efficiency and strong scalability.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Computer Vision: Multi-modal Vision

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

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.

Problem

• Develops a unified framework for multi-task time series analysis
• Integrates adaptive time-frequency fusion to capture multi-scale features
• Incorporates adaptive denoising for robust feature extraction in noisy data

Innovation

• Adaptive time-frequency fusion using Fourier and Wavelet transforms
• Automatic noise sensing and filtering for robust feature extraction
• General fusion-decoding structure with masked pre-training for transferability