HADL Framework for Noise Resilient Long-Term Time Series Forecasting

2025-02-14

AI Summary

To address performance degradation and computational inefficiency caused by extended lookback windows in high-noise long-term time series forecasting, this paper proposes a time-frequency dual-domain collaborative denoising framework. It integrates discrete wavelet transform (DWT) and discrete cosine transform (DCT) for robust joint time-frequency feature extraction, and introduces a lightweight low-rank linear prediction layer that significantly suppresses noise sensitivity and reduces parameter count via matrix low-rank approximation. The method pioneers a dual-driven denoising mechanism leveraging both time and frequency domains. It achieves state-of-the-art or leading performance across multiple benchmark datasets, demonstrating strong robustness to high noise levels and irregular sequences. Empirically, it improves inference speed by 37% and reduces GPU memory consumption by 52%.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Long-term time series forecasting is critical in domains such as finance, economics, and energy, where accurate and reliable predictions over extended horizons drive strategic decision-making. Despite the progress in machine learning-based models, the impact of temporal noise in extended lookback windows remains underexplored, often degrading model performance and computational efficiency. In this paper, we propose a novel framework that addresses these challenges by integrating the Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT) to perform noise reduction and extract robust long-term features. These transformations enable the separation of meaningful temporal patterns from noise in both the time and frequency domains. To complement this, we introduce a lightweight low-rank linear prediction layer that not only reduces the influence of residual noise but also improves memory efficiency. Our approach demonstrates competitive robustness to noisy input, significantly reduces computational complexity, and achieves competitive or state-of-the-art forecasting performance across diverse benchmark datasets. Extensive experiments reveal that the proposed framework is particularly effective in scenarios with high noise levels or irregular patterns, making it well suited for real-world forecasting tasks. The code is available in https://github.com/forgee-master/HADL.

Problem

• Noise reduction in time series
• Long-term feature extraction
• Computational efficiency improvement

Innovation

• Integrates DWT and DCT for noise reduction
• Uses lightweight low-rank linear prediction
• Enhances robustness in noisy time series