mlsanityData to 7 Oct 2026

NEST: Tackling Dataset-Level Distribution Shifts via Regime-Oriented Mixture-of-Experts

arXiv 2607.06607 ↗First posted 7 Jul 2026cs.LG cs.AIcited by 0

On the map: Mixture-of-experts → MoE for time series and graphs

Abstract (arXiv)

Accurate long-term forecasting in complex systems is frequently compromised by dataset-level distribution shifts, where diverse underlying behavioral modes and evolving system states drive the dynamic multivariate time-series. While existing methods predominantly focus on local temporal shifts, they fail to explicitly model the global structural challenge where datasets are composites of distinct operational regimes. In this paper, we propose NEST, a specialized framework designed to model and recompose these evolving structures through a two-phase dense MoE architecture. NEST first facilitates structural specialization by partitioning the dataset into distinct operational regimes through unsupervised clustering in a principled moment-entropy space. We introduce a regime-oriented router mechanism that generates initial expert weights based on temporal content, subsequently refined through geometric modulation to regime centroids. Crucially, rather than acting as monolithic predictors, individual experts function as specialized kernels that capture regime-specific dynamics by evolving unique variate-attention patterns. Extensive evaluations on diverse benchmarks, including heterogeneous network traffic and physical phenomena, demonstrate that NEST consistently achieves state-of-the-art performance. Our code and datasets are available at https://github.com/Aaralshin/NEST

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in MoE for time series and graphs, one of 12 directions in Mixture-of-experts. Builds on 11 of its 23 references that are in the map. First posted on arXiv 7 Jul 2026.

Builds on

11 of 23 references.

References · 11

  1. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  2. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  3. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  4. 2022Are Transformers Effective for Time Series Forecasting?cited by 1,400
  5. 2022FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecastingcited by 1,200
  6. 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 906
  7. 2020Deep Transformer Models for Time Series Forecasting: The Influenza Prevalence Casecited by 129
  8. 2024UniTS: A Unified Multi-Task Time Series Modelcited by 93
  9. 2023Dish-TS: A General Paradigm for Alleviating Distribution Shift in Time Series Forecastingcited by 91
  10. 2024Frequency Adaptive Normalization For Non-stationary Time Series Forecastingcited by 45
  11. 2024CESNET-TimeSeries24: Time Series Dataset for Network Traffic Anomaly Detection and Forecastingcited by 9

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series Forecasting
  2. 2026RAVEN: A Regime-Aware Variable-context Expert Network for Financial Time Series Forecasting
  3. 2026AME-TS: Anchored Mixture-of-Experts for Time Series Forecasting
  4. 2026More Experts, Worse Dynamics: Inverse Scaling and Spectral Bias in Mixture-of-Experts State-Space Models
  5. 2026DynG-Diff: A State-Aware Dynamic Guidance Diffusion Framework for Probabilistic Time Series Forecasting
  6. 2026Aurora-X: Built for Extreme Time Series Forecasting
  7. 2026Fuzzy-MoE: Interpretable Regime-Conditioned Expert Routing for Non-Stationary Multivariate Time Series Forecasting
  8. 2026Efficient Test-Time Scaling for LLM-based Time Series Forecasting