mlsanityData to 14 Oct 2026

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

arXiv 2506.05857 ↗First posted 6 Jun 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 32 references that are in the map. First posted on arXiv 6 Jun 2025.

Builds on

18 of 32 references.

References · 18

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  4. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
  5. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
  6. 2020Reformer: The Efficient Transformercited by 1,668
  7. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,476
  8. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,210
  9. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
  10. 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
  11. 2020Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networkscited by 566
  12. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 530
6 more
  1. 2020Learning under Concept Drift: A Reviewcited by 477
  2. 2015A Recurrent Latent Variable Model for Sequential Datacited by 362
  3. 2019Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecastingcited by 161
  4. 2023OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensemblingcited by 74
  5. 2022Koopman Neural Forecaster for Time Series with Temporal Distribution Shiftscited by 37
  6. 2022DDG-DA: Data Distribution Generation for Predictable Concept Drift Adaptationcited by 36

Built on by

Not cited yet.