AAAI'27 Workshop

AI4TS: AI for Time Series Analysis

Theory, Algorithms, and Applications

  • Montreal, Canada
  • Workshop date: TBD
Call for Papers → Schedule

Intro

AI for Time Series Analysis

Time series data are becoming ubiquitous across numerous real-world applications, including IoT devices, healthcare, wearable devices, smart vehicles, financial markets, biological sciences, and environmental sciences.

The availability of massive amounts of data, their complex underlying structures and distributions, and advances in high-performance computing have created a growing demand for new theories and algorithms to address fundamental challenges in time series analysis, including representation, classification, prediction, causal analysis, and multimodal learning across diverse applications.

The goal of this workshop is to provide a platform for researchers and AI practitioners from academia and industry to discuss emerging research directions, key technical challenges, and solutions for addressing these challenges in practical applications. The workshop will focus on both the theoretical and practical aspects of time series data analysis and aims to inspire innovations in theories, algorithms, and applications, especially in emerging domains such as multimodal learning and agentic AI. We will invite researchers, AI practitioners, and policymakers from related fields, including machine learning, data science, statistics, econometrics, and other disciplines, to contribute to the workshop.

01 Motivation time series data are ubiquitous anomaly forecast DATA FROM IoT devices Healthcare Wearable devices Smart vehicles Financial markets Biological sciences Environmental sciences FUNDAMENTAL CHALLENGES Representation Classification Prediction Causal analysis Multimodal learning 02 Research focus new theories and algorithms Theory Algorithms Applications EMERGING DIRECTIONS Foundation models & LLMs Multimodal learning Agentic AI BRINGING TOGETHER Academia Industry Policymakers Machine learning Data science Statistics Econometrics 03 Workshop format a full-day program at AAAI'27 Keynote talks Five invited talks from academia and industry Oral & poster papers 8-min talk + 2-min Q&A · poster session Award Ceremony 3:20 pm - 3:30 pm Panel discussion Moderator: Dongjin Song THE AI4TS WORKSHOP SERIES IJCAI'22 IJCAI'23 ICDM'23 AAAI'24 IJCAI'24 AAAI'25 WebConf'25 AAAI'26 AAAI'27 Montreal, Canada 01 Motivation time series data are ubiquitous anomaly forecast DATA FROM IoT devices Healthcare Wearable devices Smart vehicles Financial markets Biological sciences Environmental sciences FUNDAMENTAL CHALLENGES Representation Classification Prediction Causal analysis Multimodal learning 02 Research focus new theories and algorithms Theory Algorithms Applications EMERGING DIRECTIONS Foundation models & LLMs Multimodal learning Agentic AI BRINGING TOGETHER Academia Industry Policymakers Machine learning Data science Statistics Econometrics 03 Workshop format a full-day program at AAAI'27 Keynote talks Five invited talks from academia and industry Oral & poster papers 8-min talk + 2-min Q&A · poster session Award Ceremony 3:20 pm - 3:30 pm Panel discussion Moderator: Dongjin Song THE AI4TS WORKSHOP SERIES IJCAI'22 IJCAI'23 ICDM'23 AAAI'24 IJCAI'24 AAAI'25 WebConf'25 AAAI'26 AAAI'27 · Montreal, Canada
Workshop overview: motivation, research focus, the full-day program, and the AI4TS workshop series.

Topics

Topics of Interest

This workshop welcomes submissions presenting innovative solutions to a broad range of time series analysis problems. Topics of interest include, but are not limited to:

  • Time series forecasting and prediction
  • Spatio-temporal forecasting and prediction
  • Time series anomaly detection and diagnosis
  • Time series change point detection
  • Time series classification and clustering
  • Time series similarity search
  • Time series indexing
  • Time series compression
  • Time series pattern discovery
  • Time series domain adaptation and generalization
  • Time series source-free domain adaptation
  • Federated learning for time series
  • Interpretation and explanation in time series
  • Causal discovery and inference in time series
  • Bias and fairness in time series
  • Benchmarks, experimental evaluation, and comparison for time series analysis tasks
  • Foundation models and LLMs for time series analysis
  • Multimodal time series analysis
  • Agentic AI for time series analysis
  • Time series applications in various areas: E-commerce, Cloud computing, Transportation, Fintech, Healthcare, Internet of things, Wireless networks, Predictive maintenance, Education, Energy, Climate, etc.

CFP

Call for Papers

Submissions should be 4-7 pages long, excluding references, and follow the AAAI2027 template. Submissions are double-blind and author identity should not be revealed to the reviewers. An optional appendix of arbitrary length is allowed and should be put at the end of the paper (after references).

Accepted papers will be presented as posters during the workshop and listed on the website (non-archival/without proceedings). A small number of accepted papers will be selected to be presented as contributed talks (10-minute oral presentations). We also welcome submissions of unpublished papers, including those submitted/accepted to other venues if that other venue allows.

Submission link: TBD

Note: Microsoft CMT service was used for managing the peer-reviewing process for this conference. This service was provided for free by Microsoft and they bore all expenses, including costs for Azure cloud services as well as for software development and support.

  1. Prepare4-7 pages excluding references, AAAI2027 template; optional appendix after references
  2. SubmitSubmission link: TBD
  3. Double-blind reviewAuthor identity should not be revealed to the reviewers
  4. Present at AI4TSPosters for all accepted papers; selected papers as 10-minute contributed talks; listed on the website (non-archival)

Timeline

Key Dates

Workshop Paper Submission Due DateTBD23:59 AoE
Notification of Paper AcceptanceTBD23:59 AoE
AAAI AI4TS Workshop DateTBD
LocationMontreal, CanadaRoom: TBD

Schedule

Detailed Workshop Schedule

* Each oral presentation consists of 8 minutes presentation and 2 minutes Q&A.

Time (EST)SpeakerTitle
9:00 am - 9:05 amOpening Remarks
9:05 am - 9:45 amTBDKeynote Talk 1
9:45 am - 10:35 amOral Paper PresentationsOral Papers 1-5
10:35 am - 10:50 amCoffee Break
10:50 am - 11:30 amTBDKeynote Talk 2
11:30 am - 12:10 pmTBDKeynote Talk 3
12:10 pm - 2:00 pmLunch Break
2:00 pm - 2:40 pmTBDKeynote Talk 4
2:40 pm - 3:20 pmTBDKeynote Talk 5
3:20 pm - 3:30 pmAward Ceremony
3:30 pm - 3:50 pmCoffee Break
3:50 pm - 4:30 pmModerator: Dongjin SongPanel Discussion
4:30 pm - 6:00 pmPoster Session
Montreal skyline
Location: Montreal, CanadaRoom: TBD

Organizing Committee

Organizers

Dongsheng Luo

Dongsheng Luo

Presidential Assistant Professor
Singapore Management University
Qingsong Wen

Qingsong Wen

Head of AI Research & Chief Scientist
Squirrel AI Learning
Yao Xie

Yao Xie

Coca-Cola Foundation Chair and Professor
Georgia Institute of Technology
Min Wu

Min Wu

Principal Scientist II
Institute for Infocomm Research (I2R), A*STAR
Haifeng Chen

Haifeng Chen

Head Data Science and System Security Department at NEC Laboratories America
Yuriy Nevmyvaka

Yuriy Nevmyvaka

Managing Director Machine Learning Research at Morgan Stanley

Website

Webmasters

Peilin Tan

Ph.D. Student
University of Connecticut