Frequency Adaptive Normalization For Non-stationary Time Series Forecasting

2024/09/30 by Weiwei Ye, Songgaojun Deng, Ye, Weiwei +4 · 13 citations
Computer Science · Decision Sciences · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications #Stock Market Forecasting Methods #Time Series Analysis and Forecasting

paper · pdf · doi:10.48550/arxiv.2409.20371

openalex publication_date 2024/09/30 · openalex created_date 2024/10/28 · openalex updated_date 2026/07/28

Abstract

Time series forecasting typically needs to address non-stationary data with evolving trend and seasonal patterns. To address the non-stationarity, reversible instance normalization has been recently proposed to alleviate impacts from the trend with certain statistical measures, e.g., mean and variance. Although they demonstrate improved predictive accuracy, they are limited to expressing basic trends and are incapable of handling seasonal patterns. To address this limitation, this paper proposes a new instance normalization solution, called frequency adaptive normalization (FAN), which extends instance normalization in handling both dynamic trend and seasonal patterns. Specifically, we employ the Fourier transform to identify instance-wise predominant frequent components that cover most non-stationary factors. Furthermore, the discrepancy of those frequency components between inputs and outputs is explicitly modeled as a prediction task with a simple MLP model. FAN is a model-agnostic method that can be applied to arbitrary predictive backbones. We instantiate FAN on four widely used forecasting models as the backbone and evaluate their prediction performance improvements on eight benchmark datasets. FAN demonstrates significant performance advancement, achieving 7.76% ~ 37.90% average improvements in MSE.

Cited by

• A Comparative Study on How Data Normalization Affects Zero-Shot Generalization in Time Series Foundation Models
• FreIE: Low-Frequency Spectral Bias in Neural Networks for Time-Series Tasks
• DSAT-HD: Dual-Stream Adaptive Transformer with Hybrid Decomposition for Multivariate Time Series Forecasting
• ARIES: Relation Assessment and Model Recommendation for Deep Time Series Forecasting
• Online time series prediction using feature adjustment
• EventTSF: Event-Aware Non-Stationary Time Series Forecasting
• Multivariate Long-term Time Series Forecasting with Fourier Neural Filter
• FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency
• Non-stationary Diffusion For Probabilistic Time Series Forecasting
• Learning Robust Spectral Dynamics for Temporal Domain Generalization
• Temporal Query Network for Efficient Multivariate Time Series Forecasting
• Multi-Order Wavelet Derivative Transform for Deep Time Series Forecasting
• Non-Stationary Time Series Forecasting Based on Fourier Analysis and Cross Attention Mechanism

Related

• FredNormer: Frequency Domain Normalization for Non-stationary Time Series Forecasting
• Inner-Instance Normalization for Time Series Forecasting
• Wavelet-based Disentangled Adaptive Normalization for Non-stationary Times Series Forecasting
• IN-Flow: Instance Normalization Flow for Non-stationary Time Series Forecasting
• Non-Stationary Time Series Forecasting Based on Fourier Analysis and Cross Attention Mechanism