Dynamic Multi-period Experts for Online Time Series Forecasting

• URL: http://arxiv.org/abs/2603.09062v1
• Date: Tue, 10 Mar 2026 01:09:30 GMT
• Title: Dynamic Multi-period Experts for Online Time Series Forecasting
• Abstract summary: We first redefine concept drift by categorizing it into two distinct types: Recurring Drift and Emergent Drift.<n>We then propose DynaME, a novel hybrid framework designed to effectively address this dual nature of drift.<n>For Recurring Drift, DynaME employs a committee of specialized experts that are dynamically fitted to the most relevant historical periodic patterns at each time step.<n>For Emergent Drift, the framework detects high-uncertainty scenarios and shifts reliance to a stable, general expert.
• Score: 15.001287568167067
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Online Time Series Forecasting (OTSF) requires models to continuously adapt to concept drift. However, existing methods often treat concept drift as a monolithic phenomenon. To address this limitation, we first redefine concept drift by categorizing it into two distinct types: Recurring Drift, where previously seen patterns reappear, and Emergent Drift, where entirely new patterns emerge. We then propose DynaME (Dynamic Multi-period Experts), a novel hybrid framework designed to effectively address this dual nature of drift. For Recurring Drift, DynaME employs a committee of specialized experts that are dynamically fitted to the most relevant historical periodic patterns at each time step. For Emergent Drift, the framework detects high-uncertainty scenarios and shifts reliance to a stable, general expert. Extensive experiments on several benchmark datasets and backbones demonstrate that DynaME effectively adapts to both concept drifts and significantly outperforms existing baselines.

Related papers

• Drive-HWM: Hierarchical World Models for Dynamic-Latent Guided Autonomous Driving [78.83165764484562]
  Drive-HWM is a hierarchical slow--fast world modeling framework that organizes future representation prediction and action generation at complementary temporal scales.<n>Next-frame prediction encourages the fast model to capture imminent scene evolution, while one-step action generation allows decisions to be continuously updated as new observations arrive.
  arXiv  Detail & Related papers  (2026-09-03T09:21:19Z)
• Hamiltonian Spectral-Temporal Dissipative Dynamics for Sequential Recommendation [4.649779668774962]
  We introduce the Hamiltonian Spectral Recommender (HSR), which recasts preference evolution as a dissipative Hamiltonian system.<n>HSR consistently outperforms state-of-the-art Transformer-based and state space model (SSM)-based recommenders.
  arXiv  Detail & Related papers  (2026-08-26T13:04:04Z)
• Fuzzy-MoE: Interpretable Regime-Conditioned Expert Routing for Non-Stationary Multivariate Time Series Forecasting [10.050287855808307]
  Fuzzy-MoE is a fuzzy logic-based dynamic Mixture-of-Experts model.<n>It infers latent temporal states and computes expert activation strengths through learnable Gaussian membership functions.<n>It significantly outperforms mainstream forecasting methods in forecasting accuracy.
  arXiv  Detail & Related papers  (2026-08-21T05:49:32Z)
• Drift-Resistant Navigation World Model with Anchored Epipolar Guidance [81.52175010905665]
  We propose Drift-Resistant Navigation World Model, a generative model that mitigates both perceptual drift and geometric drift in conventional rollout-based navigation world models.<n>We first predict sparse future anchors that serve as stable long-range targets, and then generate intermediate frames within each chunk conditioned on both past context and future anchors.<n>Experiments on four benchmarks demonstrate consistent improvements over strong baselines in long-horizon visual quality, geometric consistency, and multi-view coherence.
  arXiv  Detail & Related papers  (2026-05-23T22:47:33Z)
• Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series Forecasting [39.362777320328256]
  We propose Dynamic TMoE, a framework that unifies architectural evolution with temporal continuity during learning phase.<n> Experiments on nine benchmarks demonstrate state-of-the-art performance, reducing MSE by 10.4% and MAE by 7.8%.
  arXiv  Detail & Related papers  (2026-05-20T03:45:22Z)
• Tackling Time-Series Forecasting Generalization via Mitigating Concept Drift [18.597913113449042]
  We identify two types of distribution shifts in time series: concept drift and temporal shift.<n>We introduce ShifTS, a method-agnostic framework designed to tackle temporal shift first and concept drift within a unified approach.
  arXiv  Detail & Related papers  (2025-10-16T15:48:52Z)
• Drift No More? Context Equilibria in Multi-Turn LLM Interactions [58.69551510148673]
  contexts drift is the gradual divergence of a model's outputs from goal-consistent behavior across turns.<n>Unlike single-turn errors, drift unfolds temporally and is poorly captured by static evaluation metrics.<n>We show that multi-turn drift can be understood as a controllable equilibrium phenomenon rather than as inevitable decay.
  arXiv  Detail & Related papers  (2025-10-09T04:48:49Z)
• DriftMoE: A Mixture of Experts Approach to Handle Concept Drifts [1.2487037582320804]
  This paper introduces DriftMoE, an online Mixture-of-Experts (MoE) architecture that addresses limitations through a novel co-training framework.<n> DriftMoE features a compact neural router that is co-trained alongside a pool of incremental Hoeffding tree experts.<n>We evaluate DriftMoE's performance across nine state-of-the-art data stream learning benchmarks spanning abrupt, gradual, and real-world drifts.
  arXiv  Detail & Related papers  (2025-07-24T14:39:20Z)
• FindRec: Stein-Guided Entropic Flow for Multi-Modal Sequential Recommendation [57.577843653775]
  We propose textbfFindRec (textbfFlexible unified textbfinformation textbfdisentanglement for multi-modal sequential textbfRecommendation)<n>A Stein kernel-based Integrated Information Coordination Module (IICM) theoretically guarantees distribution consistency between multimodal features and ID streams.<n>A cross-modal expert routing mechanism that adaptively filters and combines multimodal features based on their contextual relevance.
  arXiv  Detail & Related papers  (2025-07-07T04:09:45Z)
• CORAL: Concept Drift Representation Learning for Co-evolving Time-series [6.4314326272535896]
  Concept drift affects the reliability and accuracy of conventional analysis models.<n>This paper presents CORAL, a method that models time series as an evolving ecosystem to learn representations of concept drift.
  arXiv  Detail & Related papers  (2025-01-02T15:09:00Z)
• PDETime: Rethinking Long-Term Multivariate Time Series Forecasting from the perspective of partial differential equations [49.80959046861793]
  We present PDETime, a novel LMTF model inspired by the principles of Neural PDE solvers. Our experimentation across seven diversetemporal real-world LMTF datasets reveals that PDETime adapts effectively to the intrinsic nature of the data.
  arXiv  Detail & Related papers  (2024-02-25T17:39:44Z)
• Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective [63.60312929416228]
  textbftextitAttraos incorporates chaos theory into long-term time series forecasting. We show that Attraos outperforms various LTSF methods on mainstream datasets and chaotic datasets with only one-twelfth of the parameters compared to PatchTST.
  arXiv  Detail & Related papers  (2024-02-18T05:35:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.