Empowering Time Series Analysis with Foundation Models: A Comprehensive Survey
This survey addresses the need for an up-to-date synthesis in the rapidly evolving field of foundation models for time series analysis, benefiting researchers and practitioners by providing a structured overview and future directions.
The authors conducted a comprehensive survey on applying foundation models to time series analysis, highlighting their potential to overcome limitations of traditional task-specific methods through cross-task transferability and zero-/few-shot learning, and they introduced a modality-aware taxonomy to organize existing works and challenges.
Time series data are ubiquitous across diverse real-world applications, making time series analysis critically important. Traditional approaches are largely task-specific, offering limited functionality and poor transferability. In recent years, foundation models have revolutionized NLP and CV with their remarkable cross-task transferability, zero-/few-shot learning capabilities, and multimodal integration capacity. This success has motivated increasing efforts to explore foundation models for addressing time series modeling challenges. Although some tutorials and surveys were published in the early stages of this field, the rapid pace of recent developments necessitates a more comprehensive and in-depth synthesis to cover the latest advances. Our survey aims to fill this gap by introducing a modality-aware, challenge-oriented perspective, which reveals how foundation models pre-trained on different modalities face distinct hurdles when adapted to time series tasks. Building on this perspective, we propose a taxonomy of existing works organized by pre-training modality (time series, language, and vision), analyze modality-specific challenges and categorize corresponding solutions, discussing their advantages and limitations. Beyond this, we review real-world applications to illustrate domain-specific advancements, provide open-source codes, and conclude with potential future research directions in this rapidly evolving field.