Dual-Prototype Disentanglement: A Context-Aware Enhancement Framework for Time Series Forecasting

• URL: http://arxiv.org/abs/2601.16632v2
• Date: Tue, 27 Jan 2026 08:51:39 GMT
• Title: Dual-Prototype Disentanglement: A Context-Aware Enhancement Framework for Time Series Forecasting
• Authors: Haonan Yang, Jianchao Tang, Zhuo Li,
• Abstract summary: We propose a model-agnostic auxiliary method that equips forecasting models with the ability of pattern disentanglement and context-aware adaptation.<n>Specifically, we construct a Dynamic Dual-Prototype bank (DDP), comprising a common pattern bank with strong temporal priors to capture prevailing trend or seasonal patterns.<n>We also introduce a Disentanglement-Guided Loss (DGLoss) to ensure that each prototype bank specializes in its designated role while maintaining comprehensive coverage.
• Score: 5.764294765094398
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Time series forecasting has witnessed significant progress with deep learning. While prevailing approaches enhance forecasting performance by modifying architectures or introducing novel enhancement strategies, they often fail to dynamically disentangle and leverage the complex, intertwined temporal patterns inherent in time series, thus resulting in the learning of static, averaged representations that lack context-aware capabilities. To address this, we propose the Dual-Prototype Adaptive Disentanglement framework (DPAD), a model-agnostic auxiliary method that equips forecasting models with the ability of pattern disentanglement and context-aware adaptation. Specifically, we construct a Dynamic Dual-Prototype bank (DDP), comprising a common pattern bank with strong temporal priors to capture prevailing trend or seasonal patterns, and a rare pattern bank dynamically memorizing critical yet infrequent events, and then an Dual-Path Context-aware routing (DPC) mechanism is proposed to enhance outputs with selectively retrieved context-specific pattern representations from the DDP. Additionally, we introduce a Disentanglement-Guided Loss (DGLoss) to ensure that each prototype bank specializes in its designated role while maintaining comprehensive coverage. Comprehensive experiments demonstrate that DPAD consistently improves forecasting performance and reliability of state-of-the-art models across diverse real-world benchmarks.

Related papers

• Generative Actor Critic [74.04971271003869]
  Generative Actor Critic (GAC) is a novel framework that decouples sequential decision-making by reframing textitpolicy evaluation as learning a generative model of the joint distribution over trajectories and returns.<n>Experiments on Gym-MuJoCo and Maze2D benchmarks demonstrate GAC's strong offline performance and significantly enhanced offline-to-online improvement compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-25T06:31:11Z)
• UniDiff: A Unified Diffusion Framework for Multimodal Time Series Forecasting [90.47915032778366]
  We propose UniDiff, a unified diffusion framework for multimodal time series forecasting.<n>At its core lies a unified and parallel fusion module, where a single cross-attention mechanism integrates structural information from timestamps and semantic context from texts.<n>Experiments on real-world benchmark datasets across eight domains demonstrate that the proposed UniDiff model achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-12-08T05:36:14Z)
• TS2Vec-Ensemble: An Enhanced Self-Supervised Framework for Time Series Forecasting [1.2461503242570642]
  This paper introduces TS2Vec-Ensemble, a novel hybrid framework for time series forecasting.<n>Our approach enhances the powerful, implicitly learned dynamics from a pretrained TS2Vec encoder by fusing them with explicit, engineered time features that encode periodic cycles.<n>The results demonstrate that TS2Vec-Ensemble consistently and significantly outperforms the standard TS2Vec baseline and other state-of-the-art models.
  arXiv  Detail & Related papers  (2025-11-27T12:19:18Z)
• Leveraging Duration Pseudo-Embeddings in Multilevel LSTM and GCN Hypermodels for Outcome-Oriented PPM [4.120576565537633]
  Existing deep learning models for Predictive Process Monitoring (PPM) struggle with temporal irregularities.<n>We propose a dual input neural network strategy that separates event and sequence attributes, using a duration-aware pseudo-embedding matrix.<n>Our results demonstrate the benefits of explicit temporal encoding and provide a flexible design for robust, real-world PPM applications.
  arXiv  Detail & Related papers  (2025-11-24T07:06:08Z)
• ForecastGAN: A Decomposition-Based Adversarial Framework for Multi-Horizon Time Series Forecasting [0.5213778368155993]
  Time series forecasting is essential across domains from finance to supply chain management.<n>This paper introduces ForecastGAN, a novel decomposition based adversarial framework for multi-horizon predictions.<n>ForecastGAN consistently outperforms state-of-the-art transformer models for short-term forecasting while remaining competitive for long-term horizons.
  arXiv  Detail & Related papers  (2025-11-06T15:19:23Z)
• Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories [58.988535279557546]
  We introduce textbf sycophancy Mitigation through Adaptive Reasoning Trajectories.<n>We show that SMART significantly reduces sycophantic behavior while preserving strong performance on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2025-09-20T17:09:14Z)
• STEP: Structured Training and Evaluation Platform for benchmarking trajectory prediction models [7.927039780654076]
  We introduce STEP -- a new benchmarking framework that addresses limitations by providing a unified interface for multiple datasets.<n>We demonstrate the capabilities of STEP in a number of experiments which reveal 1) the limitations of widely-used testing procedures, 2) the importance of joint modeling of agents for better predictions of interactions, and 3) the vulnerability of current state-of-the-art models against both distribution shifts and targeted attacks by adversarial agents.
  arXiv  Detail & Related papers  (2025-09-18T09:56:16Z)
• Foundation Models for Demand Forecasting via Dual-Strategy Ensembling [11.926658499983446]
  We propose a unified ensemble framework that enhances the performance of foundation models for sales forecasting in real-world supply chains.<n>Our method combines two complementary strategies: (1) Hierarchical Ensemble (HE), which partitions training and inference by semantic levels to capture localized patterns; and (2) Architectural Ensemble (AE), which integrates predictions from diverse model backbones to mitigate bias and improve stability.
  arXiv  Detail & Related papers  (2025-07-29T17:56:38Z)
• Advancing Reliable Test-Time Adaptation of Vision-Language Models under Visual Variations [67.35596444651037]
  Vision-language models (VLMs) exhibit remarkable zero-shot capabilities but struggle with distribution shifts in downstream tasks when labeled data is unavailable.<n>We propose a Reliable Test-time Adaptation (ReTA) method that enhances reliability from two perspectives.
  arXiv  Detail & Related papers  (2025-07-13T05:37:33Z)
• Learning Time-Aware Causal Representation for Model Generalization in Evolving Domains [50.66049136093248]
  We develop a time-aware structural causal model (SCM) that incorporates dynamic causal factors and the causal mechanism drifts.<n>We show that our method can yield the optimal causal predictor for each time domain.<n>Results on both synthetic and real-world datasets exhibit that SYNC can achieve superior temporal generalization performance.
  arXiv  Detail & Related papers  (2025-06-21T14:05:37Z)
• LARES: Latent Reasoning for Sequential Recommendation [96.26996622771593]
  We present LARES, a novel and scalable LAtent REasoning framework for Sequential recommendation.<n>Our proposed approach employs a recurrent architecture that allows flexible expansion of reasoning depth without increasing parameter complexity.<n>Our framework exhibits seamless compatibility with existing advanced models, further improving their recommendation performance.
  arXiv  Detail & Related papers  (2025-05-22T16:22:54Z)
• UltraSTF: Ultra-Compact Model for Large-Scale Spatio-Temporal Forecasting [34.03281105180512]
  We propose UltraSTF, which integrates a cross-period forecasting component with an ultra-compact shape bank component.<n>Our model efficiently captures recurring patterns in time series using the attention mechanism of the shape bank component.<n>UltraSTF achieves state-of-the-art performance on the LargeST benchmark while utilizing fewer than 0.2% of the parameters required by the second-best methods.
  arXiv  Detail & Related papers  (2025-02-28T01:35:51Z)
• Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift [51.01356105618118]
  Time series often exhibit complex non-uniform distribution with varying patterns across segments, such as season, operating condition, or semantic meaning.<n>Existing approaches, which typically train a single model to capture all these diverse patterns, often struggle with the pattern drifts between patches.<n>We propose TFPS, a novel architecture that leverages pattern-specific experts for more accurate and adaptable time series forecasting.
  arXiv  Detail & Related papers  (2024-10-13T13:35:29Z)

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.