Wavelet-based Disentangled Adaptive Normalization for Non-stationary Times Series Forecasting

2025/06/06 by Junpeng Lin, Lin, Junpeng, Tian Lan +15
Computer Science · Decision Sciences · Engineering · #FOS: Computer and information sciences #Forecasting Techniques and Applications #Machine Learning (cs.LG) #Time Series Analysis and Forecasting #Traffic Prediction and Management Techniques

paper · pdf · doi:10.48550/arxiv.2506.05857

openalex publication_date 2025/06/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Forecasting non-stationary time series is a challenging task because their statistical properties often change over time, making it hard for deep models to generalize well. Instance-level normalization techniques can help address shifts in temporal distribution. However, most existing methods overlook the multi-component nature of time series, where different components exhibit distinct non-stationary behaviors. In this paper, we propose Wavelet-based Disentangled Adaptive Normalization (WDAN), a model-agnostic framework designed to address non-stationarity in time series forecasting. WDAN uses discrete wavelet transforms to break down the input into low-frequency trends and high-frequency fluctuations. It then applies tailored normalization strategies to each part. For trend components that exhibit strong non-stationarity, we apply first-order differencing to extract stable features used for predicting normalization parameters. Extensive experiments on multiple benchmarks demonstrate that WDAN consistently improves forecasting accuracy across various backbone model. Code is available at this repository: https://github.com/MonBG/WDAN.

Citations

• OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling
• Koopman Neural Forecaster for Time Series with Temporal Distribution Shifts
• FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
• DDG-DA: Data Distribution Generation for Predictable Concept Drift Adaptation
• Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
• Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
• Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
• Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
• Reformer: The Efficient Transformer
• Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting
• An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
• Attention Is All You Need
• Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks
• A Recurrent Latent Variable Model for Sequential Data
• Adam: A Method for Stochastic Optimization
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Long Short-Term Memory

Related

• WEITS: A Wavelet-enhanced residual framework for interpretable time series forecasting
• Enhancing Foundation Models for Time Series Forecasting via Wavelet-based Tokenization
• Frequency Adaptive Normalization For Non-stationary Time Series Forecasting
• Leveraging Non-Decimated Wavelet Packet Features and Transformer Models for Time Series Forecasting
• FredNormer: Frequency Domain Normalization for Non-stationary Time Series Forecasting