FM4TS: AAAI'25 Tutorial




Foundation Models


for Time Series:




Theory, Algorithms, and Applications

Tuesday, February 25, Room 119A

In recent years, foundation models (FMs) have significantly enhanced various tasks and transformed model design in time series analysis. In this manuscript, We propose a comprehensive half-day tutorial at AAAI'25, tailored for professionals, researchers, and practitioners interested in utilizing FMs for time series analysis. This tutorial offers insights into FM theory, implementation, and practical applications, including principles, pre-processing techniques, and modeling strategies. Attendees will also learn best practices for integrating FMs into workflows and exploring applications in diverse fields, such as finance, healthcare, and transportation. Sponsored by Squirrel AI, the tutorial promises enhanced understanding, practical skills acquisition, and networking opportunities, bridging theory with practice.

Detailed Schedule

Time Speaker Title
2:00-2:10PM Dongjin Song Opening and Introduction
2:10-2:20PM Zepu Wang   Revisiting Conventional Methods for Time Series
2:20-3:00PM Zepu Wang What Can LLM Tell Us about Time Series Analysis?
3:00-4:00PM - Break
4:00-5:00PM Dongjin Song Empowering Time Series Analysis with Large Langurage Models: A Survey
5:00-5:40PM Ming Jin Methodologies of Time Series Foundation Models
30 min Ming Jin Future Directions
 

Organizers

 

Yuxuan Liang

Assistant Professor
Hong Kong University of Science and Technology (Guangzhou).

 

Dongjin Song

Assistant Professor, University of Connecticut

 

Shirui Pan

Professor
Griffith University, Australia

 

Qingsong Wen

Head of AI Research & Chief Scientist
Squirrel Ai

 

Ming Jin

Assistant Professor, Griffith University

 

Jiaxi Hu

Ph.D.
Hong Kong University of Science and Technology (Guangzhou)

 

Yushan Jiang

Ph.D.,
University of Connecticut

 

Reference

 

* Foundation Models for Time Series Analysis: A Tutorial and Survey, KDD 2024.

 
 

* Position: What Can Large Language Models Tell Us about Time Series Analysis, ICML 2024.

 
 

* Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects, TPAMI 2024.

 
 

* A Survey on Graph Neural Networks for Time Series: Forecasting, Classification, Imputation, and Anomaly Detection, TPAMI 2024.

 
 

* Empowering Time Series Analysis with Large Language Models: A Survey, IJCAI 2024.

 
 

* Transformers in Time Series: A Survey, IJCAI 2023.

 
 

* Time Series Data Augmentation for Deep Learning: A Survey, IJCAI 2021.

 
 

* Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook, arXiv 2023.

 
 

* Deep Learning for Multivariate Time Series Imputation: A Survey, arXiv 2024.

 
 

* A Survey on Diffusion Models for Time Series and Spatio-Temporal Data, arXiv 2024.

 
 

* A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challenges, arXiv 2024.

 
 

* Time Series Analysis for Education: Methods, Applications, and Future Directions, 2024.