# Towards Non-Stationary Time Series Forecasting with Temporal Stabilization and Frequency Differencing

arXiv: https://arxiv.org/abs/2511.08229 · HTML: https://mlsanity.com/paper/2511.08229/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2025.

## Built on by (most cited first, 10 of 10)

- [TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation](https://mlsanity.com/paper/2601.13653/) (2026)
- [Empowering Time Series Analysis with Large-Scale Multimodal Pretraining](https://mlsanity.com/paper/2602.05646/) (2026)
- [WaveMoE: A Wavelet-Enhanced Mixture-of-Experts Foundation Model for Time Series Forecasting](https://mlsanity.com/paper/2604.10544/) (2026)
- [QiYao-M: Multimodal Time Series Foundation Model with Role-Aware Modeling of Endogenous and Exogenous Modalities](https://mlsanity.com/paper/2609.34842/) (2026)
- [Beyond Uniform Tokens: Adaptive Compression for Time Series Language Models](https://mlsanity.com/paper/2606.13624/) (2026)
- [DecoVAE: a Lightweight Interpretable Trend-Seasonal VAE Framework for Efficient Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2608.20052/) (2026)
- [DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2609.32363/) (2026)
- [XMatch: Enhancing Covariate-Aware Time Series Forecasting through Tree-Structured Exogenous Matching](https://mlsanity.com/paper/2609.34939/) (2026)
- [EvoCast: Reliable Autonomous Research Agents for Iterative Forecasting Architecture Evolution](https://mlsanity.com/paper/2610.04517/) (2026)
- [Beyond Static Positional Encoding: Bayesian Time-aware Attention for Non-Stationary Long-term Time Series Forecasting](https://mlsanity.com/paper/2610.19603/) (2026)

## Abstract (arXiv)

Time series forecasting is critical for decision-making across dynamic domains such as energy, finance, transportation, and cloud computing. However, real-world time series often exhibit non-stationarity, including temporal distribution shifts and spectral variability, which pose significant challenges for long-term time series forecasting. In this paper, we propose DTAF, a dual-branch framework that addresses non-stationarity in both the temporal and frequency domains. For the temporal domain, the Temporal Stabilizing Fusion (TFS) module employs a non-stationary mix of experts (MOE) filter to disentangle and suppress temporal non-stationary patterns while preserving long-term dependencies. For the frequency domain, the Frequency Wave Modeling (FWM) module applies frequency differencing to dynamically highlight components with significant spectral shifts. By fusing the complementary outputs of TFS and FWM, DTAF generates robust forecasts that adapt to both temporal and frequency domain non-stationarity. Extensive experiments on real-world benchmarks demonstrate that DTAF outperforms state-of-the-art baselines, yielding significant improvements in forecasting accuracy under non-stationary conditions. All codes are available at https://github.com/decisionintelligence/DTAF.