通过频域分解实现可解释且鲁棒的时间序列预测
A Unified Frequency Domain Decomposition Framework for Interpretable and Robust Time Series Forecasting
- 分离振幅与相位独立建模，提升模型可解释性
- 在长期预测基准上优于现有模型，显著提升预测性能
- 适合需要理解时序规律的工业与金融场景
当前时间序列预测方法多基于深度学习模型，无论在时域还是频域，通常以黑箱方式编码数据，依赖仅基于预测性能的试错优化，导致可解释性和理论理解不足。同时，时间与频率域的数据分布动态变化带来关键挑战。本文提出FIRE——一种统一的频域分解框架，为多种时间序列提供数学抽象，实现可解释且鲁棒的预测。FIRE引入四项创新：(i) 独立建模振幅与相位分量，(ii) 自适应学习频率基成分权重，(iii) 靶向设计损失函数，(iv) 针对稀疏数据的新训练范式。大量实验表明，FIRE在长期预测基准上持续优于现有先进模型，不仅预测性能更优，且显著提升时间序列可解释性。
原文摘要 · Abstract (English)
Current approaches for time series forecasting, whether in the time or frequency domain, predominantly use deep learning models based on linear layers or transformers. They often encode time series data in a black-box manner and rely on trial-and-error optimization solely based on forecasting performance, leading to limited interpretability and theoretical understanding. Furthermore, the dynamics in data distribution over time and frequency domains pose a critical challenge to accurate forecasting. We propose FIRE, a unified frequency domain decomposition framework that provides a mathematical abstraction for diverse types of time series, so as to achieve interpretable and robust time series forecasting. FIRE introduces several key innovations: (i) independent modeling of amplitude and phase components, (ii) adaptive learning of weights of frequency basis components, (iii) a targeted loss function, and (iv) a novel training paradigm for sparse data. Extensive experiments demonstrate that FIRE consistently outperforms state-of-the-art models on long-term forecasting benchmarks, achieving superior predictive performance and significantly enhancing interpretability of time series
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。