Foundation Models for Time Series: A Survey

📅 2025-04-05
📈 Citations: 0
Influential: 0
📄 PDF

career value

177K/year
🤖 AI Summary
The time-series foundation model (TSFM) field lacks a systematic taxonomy, hindering comparative analysis and principled design. Method: We propose the first multi-dimensional taxonomy tailored to Transformer-based TSFMs, spanning five dimensions: architectural design, forecasting paradigm, variable dimensionality, scale/complexity, and pretraining objective functions—introducing objective function type as a novel classification criterion to unify capability characterization and design rationale. Through comprehensive literature review, architectural analysis, task mapping, and paradigm comparison, we systematically cover mainstream modeling approaches—including patch-based and raw-sequence methods. Contribution/Results: This taxonomy establishes a structured knowledge graph for TSFMs, clarifying technological trends, exposing critical research gaps, and providing a principled foundation for developing scalable, interpretable, and multi-task-cooperative time-series foundation models.

Technology Category

Application Category

📝 Abstract
Transformer-based foundation models have emerged as a dominant paradigm in time series analysis, offering unprecedented capabilities in tasks such as forecasting, anomaly detection, classification, trend analysis and many more time series analytical tasks. This survey provides a comprehensive overview of the current state of the art pre-trained foundation models, introducing a novel taxonomy to categorize them across several dimensions. Specifically, we classify models by their architecture design, distinguishing between those leveraging patch-based representations and those operating directly on raw sequences. The taxonomy further includes whether the models provide probabilistic or deterministic predictions, and whether they are designed to work with univariate time series or can handle multivariate time series out of the box. Additionally, the taxonomy encompasses model scale and complexity, highlighting differences between lightweight architectures and large-scale foundation models. A unique aspect of this survey is its categorization by the type of objective function employed during training phase. By synthesizing these perspectives, this survey serves as a resource for researchers and practitioners, providing insights into current trends and identifying promising directions for future research in transformer-based time series modeling.
Problem

Research questions and friction points this paper is trying to address.

Surveying transformer-based foundation models for time series analysis
Classifying models by architecture, prediction type, and data handling
Identifying trends and future research in time series modeling
Innovation

Methods, ideas, or system contributions that make the work stand out.

Transformer-based models for time series analysis
Novel taxonomy for pre-trained foundation models
Classification by architecture and objective function
S
Siva Rama Krishna Kottapalli
Dell Technologies, Hopkinton, MA, USA
K
Karthik Hubli
Dell Technologies, Hopkinton, MA, USA
S
Sandeep Chandrashekhara
Dell Technologies, Hopkinton, MA, USA
G
Garima Jain
University of Massachusetts Lowell, Lowell, MA, USA
S
Sunayana Hubli
University of Massachusetts Lowell, Lowell, MA, USA
G
Gayathri Botla
University of Massachusetts Lowell, Lowell, MA, USA
R
Ramesh Doddaiah
Worcester Polytechnic Institute, Worcester, MA, USA