Modèles de Fondation et Ajustement : Vers une Nouvelle Génération de Modèles pour la Prévision des Séries Temporelles

2025-11-27

AI Summary

To address the weak zero-shot generalization capability in long-horizon time series forecasting, this paper proposes a foundation model framework for time series prediction. Inspired by large language model paradigms, it employs self-supervised pretraining on large-scale heterogeneous time series data to learn general-purpose temporal representations. Crucially, it innovatively unifies point forecasting and probabilistic forecasting within a single modeling objective and introduces a lightweight fine-tuning strategy for downstream adaptation. This approach transcends conventional task-specific architectures, significantly enhancing zero-shot forecasting performance on unseen datasets. Experiments demonstrate that the fine-tuned model achieves an average 18.7% reduction in MAE on long-horizon forecasting tasks. Moreover, it exhibits strong cross-domain adaptability and practical utility across multi-source, multi-frequency, and multi-domain time series. The work establishes a novel paradigm for time series foundation model research.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Natural Language Processing: (Large) Language Models
• Cognitive Modeling & Cognitive Systems: Other Foundations of Cognitive Modeling & Systems

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Inspired by recent advances in large language models, foundation models have been developed for zero-shot time series forecasting, enabling prediction on datasets unseen during pretraining. These large-scale models, trained on vast collections of time series, learn generalizable representations for both point and probabilistic forecasting, reducing the need for task-specific architectures and manual tuning. In this work, we review the main architectures, pretraining strategies, and optimization methods used in such models, and study the effect of fine-tuning after pretraining to enhance their performance on specific datasets. Our empirical results show that fine-tuning generally improves zero-shot forecasting capabilities, especially for long-term horizons.

Problem

• Developing foundation models for zero-shot time series forecasting
• Studying fine-tuning effects to improve forecasting on specific datasets
• Reducing need for task-specific architectures and manual tuning

Innovation

• Foundation models enable zero-shot time series forecasting
• Models learn generalizable representations from vast datasets
• Fine-tuning enhances zero-shot forecasting for long-term horizons