Attention-based Experience Replay Framework for Continual Learning of Agnostic Time Series Forecasting Models

• URL: http://arxiv.org/abs/2607.20493v1
• Date: Fri, 12 Jun 2026 11:44:05 GMT
• Title: Attention-based Experience Replay Framework for Continual Learning of Agnostic Time Series Forecasting Models
• Abstract summary: Continual learning aims to develop models capable of adapting incrementally while maintaining a balance between stability and plasticity under computational constraints.<n>We introduce a novel framework for continual time series forecasting, designed to extend existing static forecasting models.<n>Results show that our approach effectively increases or maintains predictive performance over time while reducing retraining costs and data requirements.
• Score: 0.9668407688201359
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning has led to remarkable progress in artificial intelligence, particularly in robotics, imaging and sound processing. However, a major limitation of neural networks remains their strong dependence on large and stationary datasets. In many real-world applications, these conditions are rarely met due to evolving and dynamic environments where data distributions change over time. Continual learning aims to address this challenge by developing models capable of adapting incrementally while maintaining a balance between stability and plasticity under computational constraints. In this work, we introduce a novel framework for continual time series forecasting, designed to extend existing static forecasting models commonly used in the literature by incorporating an Experience Replay strategy guided by Attention mechanisms. This approach allows the model to adapt dynamically to new contexts while preserving prior knowledge, effectively mitigating catastrophic forgetting. The framework is evaluated on standard forecasting benchmarks as well as on a piezometric dataset exhibiting diverse temporal behaviors. Results show that our approach effectively increases or maintains predictive performance over time while reducing retraining costs and data requirements, thus facilitating the deployment of forecasting models in dynamic and real-world settings.

Related papers

• LeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Scheduling [74.94985663101906]
  We present LeapTS, a novel framework that reformulates time series forecasting as a dynamic scheduling process over the prediction horizon.<n>We show that LeapTS improves overall forecasting performance by at least 7.4% while achieving a 2.6$times$ to 5.3$times$ inference speedup over representative Transformer-based models.
  arXiv  Detail & Related papers  (2026-05-11T09:54:02Z)
• On Neural Scaling Laws for Weather Emulation through Continual Training [76.70310203875866]
  We study neural scaling in Scientific Machine Learning, focusing on models for weather forecasting.<n>To analyze scaling behavior in as simple a setting as possible, we adopt a minimal, scalable, general-purpose Swin Transformer architecture.<n>We show that models trained in this minimalist way follow predictable scaling trends and even outperform standard cosine learning rate schedules.
  arXiv  Detail & Related papers  (2026-03-26T17:37:25Z)
• Seeking SOTA: Time-Series Forecasting Must Adopt Taxonomy-Specific Evaluation to Dispel Illusory Gains [17.650604674194984]
  We argue that the current practice of evaluating AI/ML time-series forecasting models obscures real progress by overlooking the performance of efficient classical methods.<n>We demonstrate that these "standard" datasets often exhibit dominant autocorrelation patterns and seasonal cycles that can be effectively captured by simpler linear or statistical models.
  arXiv  Detail & Related papers  (2026-03-16T16:34:26Z)
• Entropy-Guided Token Dropout: Training Autoregressive Language Models with Limited Domain Data [89.96277093034547]
  We introduce EntroDrop, an entropy-guided token dropout method that functions as structured data regularization.<n>We show that EntroDrop consistently outperforms standard regularization baselines and maintains robust performance throughout extended multi-epoch training.
  arXiv  Detail & Related papers  (2025-12-29T12:35:51Z)
• Structured Noise Modeling for Enhanced Time-Series Forecasting [0.0]
  This work introduces a forecast-blur-denoise framework that improves temporal fidelity through structured noise modeling.<n> Experiments across electricity, traffic, and solar datasets show consistent gains in multi-horizon accuracy and stability.<n>This framework contributes to more trustworthy AI systems used in forecasting-driven decision support across energy, infrastructure, and other time-critical domains.
  arXiv  Detail & Related papers  (2025-11-24T19:44:46Z)
• Deep Generative Continual Learning using Functional LoRA: FunLoRA [12.547444644243543]
  A common strategy consists in retraining the generative model on its own synthetic data in order to mitigate forgetting.<n>We propose a novel and more expressive conditioning mechanism for generative models based on low rank adaptation (LoRA)<n>Our proposed parameter-efficient fine-tuning (PEFT) method surpasses prior state-of-the-art results based on diffusion models.
  arXiv  Detail & Related papers  (2025-10-03T00:18:05Z)
• Temporal Knowledge Distillation for Time-Sensitive Financial Services Applications [7.1795069620810805]
  Anomaly detection is frequently used in key compliance and risk functions such as financial crime detection fraud and cybersecurity. Keeping up with the rapid changes by retraining the models with the latest data patterns introduces pressures in balancing the historical and current patterns. The proposed approach provides advantages in retraining times while improving the model performance.
  arXiv  Detail & Related papers  (2023-12-28T03:04:30Z)
• Learning Robust Precipitation Forecaster by Temporal Frame Interpolation [65.5045412005064]
  We develop a robust precipitation forecasting model that demonstrates resilience against spatial-temporal discrepancies. Our approach has led to significant improvements in forecasting precision, culminating in our model securing textit1st place in the transfer learning leaderboard of the textitWeather4cast'23 competition.
  arXiv  Detail & Related papers  (2023-11-30T08:22:08Z)
• OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning [67.07363529640784]
  We propose OpenSTL to categorize prevalent approaches into recurrent-based and recurrent-free models. We conduct standard evaluations on datasets across various domains, including synthetic moving object trajectory, human motion, driving scenes, traffic flow and forecasting weather. We find that recurrent-free models achieve a good balance between efficiency and performance than recurrent models.
  arXiv  Detail & Related papers  (2023-06-20T03:02:14Z)
• Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representations [15.797295258800638]
  We introduce a novel modeling approach for time series imputation and forecasting, tailored to address the challenges often encountered in real-world data. Our method relies on a continuous-time-dependent model of the series' evolution dynamics. A modulation mechanism, driven by a meta-learning algorithm, allows adaptation to unseen samples and extrapolation beyond observed time-windows.
  arXiv  Detail & Related papers  (2023-06-09T13:20:04Z)
• Continual Visual Reinforcement Learning with A Life-Long World Model [55.05017177980985]
  We present a new continual learning approach for visual dynamics modeling.<n>We first introduce the life-long world model, which learns task-specific latent dynamics.<n>Then, we address the value estimation challenge for previous tasks with the exploratory-conservative behavior learning approach.
  arXiv  Detail & Related papers  (2023-03-12T05:08:03Z)
• Leveraging the structure of dynamical systems for data-driven modeling [111.45324708884813]
  We consider the impact of the training set and its structure on the quality of the long-term prediction. We show how an informed design of the training set, based on invariants of the system and the structure of the underlying attractor, significantly improves the resulting models.
  arXiv  Detail & Related papers  (2021-12-15T20:09:20Z)

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.