IJCAI'23 Workshop

AI4TS: AI for Time Series


Theory, Algorithms, and Applications

Time series data are becoming ubiquitous in numerous real world applications, e.g., IoT devices, healthcare, wearable devices, smart vehicles, financial markets, biological sciences, environmental sciences, etc. Given the availability of massive amounts of data, their complex underlying structures/distributions, together with the high-performance computing platforms, there is a great demand for developing new theories and algorithms to tackle fundamental challenges (e.g., representation, classification, prediction, causal analysis, etc.) in various types of applications. The goal of this workshop is to provide a platform for researchers and AI practitioners from both academia and industry to discuss potential research directions, key technical issues, and present solutions to tackle related challenges in practical applications. The workshop will focus on both the oretical and practical aspects of time series data analysis and aims to trigger research innovations in theories, algorithms, and applications. We will invite researchers and AI practitioners from the related areas of machine learning, data science, statistics, econometrics, and many others to contribute to this workshop.

This workshop encourages submissions of innovative solutions for a broad range of time series analysis problems. Topics of interest include but are not limited to the following:

  • 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
  • Interpretation and explanation in time series
  • Causal inference in time series
  • Bias and fairness in time series
  • Federated learning and security in time series
  • Benchmarks, experimental evaluation, and comparison for time series analysis tasks
  • Time series applications in various areas: E-commerce, Cloud computing, Transportation, Fintech, Healthcare, Internet of things, Wireless networks, Predictive maintenance, Energy, and Climate, etc.

Call for Papers

Contact with us: ai4ts.ijcai@gmail.com

Submissions should be 4-7 pages long, excluding references, and follow IJCAI-23 template. Submissions are single-blind and author identity will 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 list on the website (non-archival/without proceedings). Besides, a small number of accepted papers will be selected to be presented as contributed talks. We also welcome submissions of unpublished papers, including those that are submitted/accepted to other venues if that other venue allows so.

Submission link: https://cmt3.research.microsoft.com/AI4TS2023/

Any questions may be directed to the workshop e-mail address: ai4ts.ijcai@gmail.com

Key Dates


Workshop Paper Submission Due Date: May 24th, 2023(AoE)

Notification of Paper Acceptance: June 4th, 2023 June 9th, 2023

IJCAI-23 Workshops: August 20th, 2023

Detailed Workshop Schedule:

August 20th

Location: Almaty 6105 @ Sheraton Grand Macao

Zoom Link:

9:00 am - 9:10 amDr. Dongjin SongOpening Remarks
9:10 am - 10:00 amDr. Chris WhiteKeynote Talk 1: Time Dynamics: Physics, Simulation, and Machine Learning
10:00 am - 10:50 amProf. Yan LiuKeynote Talk 2: Frontiers of Machine Learning for Time Series Modeling and Analysis
10:50 am – 11:10 amCoffee Break 
11:10 am – 12:00 pmProf. Mingsheng LongKeynote Talk 3: Towards Foundation Models for Time Series Analysis
12:00pm – 12: 30 pmOral paper 1-2

Paper 1: AutoTCL: Automated Time Series Contrastive Learning with Adaptive Augmentations

Paper 2: Uncertainty-Aware Quickest Change Detection

12:30 pm - 2:00 pmLunch 
2:00 pm – 2:50 pmProf. Albert BifetKeynote Talk 4: Green AI
2:50pm – 3:40 pmProf. Yi WangKeynote Talk 5: AI for Time Series Analysis in Power and Energy Systems
3:40pm – 4:00pmCoffee Break 
4:00pm – 4: 30pmOral paper 3-4

Paper 3: Sequential Predictive Conformal Inference for Time Series

Paper 4: Real World Time Series Benchmark Datasets with Temporal Distribution Shifts: Global Crude Oil Asset Price and Volatility

4:30pm – 4: 40pm Award Ceremony
4:40pm - 5: 40pm Poster Session
5:40pm – 5: 45pmDr. Haifeng ChenClosing Remarks


Dr. Christopher White

NEC Labs America

Title: Time Dynamics: Physics, Simulation, and Machine Learning.

In this talk, I will talk about physics approaches to quantitative time dynamics, agent-based modeling techniques for time dynamics over large time scales, and data driven machine learning based methods for systems where suitable physical models don’t exist. Hopefully with a conclusion about how one might combine these methods for the modern treatment of time dynamics in complex systems.

Prof. Yan Liu

University of Southern California

Title: Frontiers of Machine Learning for Time Series Modeling and Analysis

Recent development in deep learning has spurred research advances in time series modeling and analysis. Practical applications of time series raise a series of new challenges, such multi-resolution, multimodal, missing value, distributeness, and interpretability. In this talk, I will discuss machine-learning solutions to address these challenges and future directions for time series research.

Prof. Mingsheng Long

Associate Professor, Tsinghua University

Title: Towards Foundation Models for Time Series Analysis

Large-scale time series data are perceived and collected from IoT devices, which is the main body of industrial big data. Time series are discrete observations sampled from continuous physical systems with complex patterns and variations. In this talk, I will introduce deep learning models for time series analysis, including Autoformer, TimesNet, and Koopa, which are consequences of seamless integration of Fourier analysis, self-correlation, cross-correlation, non-stationarity, linear dynamical system and other design principles into deep learning. I will also highlight the cover article published in Nature Machine Intelligence, presenting the Corrformer model for interpretable weather forecasting of global automatic stations, which was deployed as a real-time weather service in the Beijing 2022 Winter Olympics. With this talk, I want to comment on the path towards general foundation models for time series analysis.

Prof. Albert Bifet

Director of the AI Institute at the University of Waikato

Title: Green AI

In this talk, we will talk about Green AI, focusing on its two main aspects: using AI to tackle environmental issues and making AI systems more environmentally friendly. using incremental approaches. As AI becomes increasingly important for problem-solving and research, it is essential to integrate it into sustainability efforts. We will examine how AI is not only giving researchers a competitive advantage but also playing a key role in creating a more sustainable future.

Jan Gasthaus

Prof. Yi Wang

Univerisity of Hong Kong
Assistant Professor

Titile: AI for Time Series Analysis in Power and Energy Systems

An extensive range of time series data, such as electricity consumption, renewable energy output, nodal voltage magnitude, and phase data, are generated by power and energy systems. Gaining a comprehensive understanding of this time series data is crucial for secure, cost-effective system operation and the integration of renewable energy sources. This presentation will demonstrate the application of AI-based time series analysis in power and energy systems, encompassing non-intrusive monitoring, load profiling, energy forecasting, synthetic data generation, etc.

Accepted Oral Papers


* Real World Time Series Benchmark Datasets with Temporal Distribution Shifts: Global Crude Oil Asset Price , Volatility
 Pranay Pasula

* AutoTCL: Automated Time Series Contrastive Learning with Adaptive Augmentations
 Xu Zheng , Tianchun Wang , Wei Cheng, Aitian Ma , Haifeng Chen , Mo Sha , Dongsheng Luo

* Uncertainty-Aware Quickest Change Detection
 Yancheng Huang , Kai Yang1 , Chengbo Qiu , Jiangfan Zhang , Xiaodong Wang

* Sequential Predictive Conformal Inference for Time Series
  Chen Xu , Yao Xie


Accepted Posters


* Periodicity Enhanced Long Short-term Memory Network for Wind Power Forecasting
 Zhechun Liang , Kexuan Shi , Wu Li , Weiwei Wang

* Causal Structural Learning from Time Series: A Convex Optimization Approach 
Song Wei , Yao Xie

* Refining the Optimization Target for Automatic Univariate Time Series Anomaly Detection in Monitoring Services  
Manqing Dong , Zhanxiang Zhao , Yitong Geng , Wentao Li , Wei Wang , Huai Jiang

* Clustering-based Numerosity Reduction for Cloud Workload Forecasting  
Andrea Rossi , Andrea Visentin , Steven Prestwich , Kenneth N. Brown

* Self-Supervised Learning for Time Series: Contrastive or Generative?  
Ziyu Liu , Azadeh Alavi , Minyi Li , Xiang Zhang

* Graph Neural Network-based Tourism Demand Forecasting in Multivariate Time Series 
Qun Yang , Weijun Li , Wencai Du

* AVGNets: Angular Visibility Graph Networks with Probability Attention for Time Series Forecasting 
Shengzhong Mao , Xiao-Jun Zeng

* TACOformer:Token-channel compounded Cross Attention for Multimodal Emotion Recognition 
Xinda Li

* Robustness and Generalization Performance of Deep Learning Models on Cyber-Physical Systems: A Comparative Study 
Alexander Windmann , Henrik Steude , Oliver Niggemann

* MDDNet: EEG-based Transformer with Domain Adversarial Learning for Major Depression Disorder Diagnosis 
Shaozhe Liu , Leike An , Ziyu Jia

* Genetic Algorithm Based Architecture Search in Stacked LSTM Network for Time Series Forecasting 
Linzhe Cai , Xinghuo Yu , Chen Liu , Chaojie Li , Andrew Eberhard

* Temporal information embedding neural network for structural seismic response prediction 
Chengbo Wang Poster Link

* What Constitutes Good Contrastive Learning in Time-Series Forecasting? 
Chiyu Zhang , Qi Yan , Lili Meng , Tristan Sylvain

* Embarrassingly Simple MixUp for Time-series 
Karan Aggarwal , Jaideep Srivastava

* MADS: Modulated Auto-Decoding SIREN for time series imputation 
Tom Bamford , Elizabeth Fons , Yousef El-laham , Svitlana Vyetrenko

* Perturbing a Neural Network to Infer Effective Connectivity: Evidence from Synthetic EEG Data 
Peizhen Yang , Xinke Shen , Zongsheng Li , Zixiang Luo , Kexin Lou, Quanying Liu

General Chairs

The following are arranged in alphabetical order


Dongjin Song

Assistant Professor, University of Connecticut


Qingsong Wen

Staff Engineer and Manager
DAMO Academy Decision Intelligence Lab, Alibaba Group


Sanjay Purushotham

Assistant professor
University of Maryland Baltimore County


Haifeng Chen

Data Science and System Security Department at NEC Laboratories America

Program Chairs

The following are arranged in alphabetical order


Liang Sun

Senior Staff Engineer
DAMO Academy-Decision Intelligence Lab, Alibaba Group


Shirui Pan

Griffith University


Wei Cheng

Senior Researcher
NEC Labs America


Yingjie Zhou

Associate Professor
Sichuan University


Yifeng Gao

Assistant Professor
University of Texas Rio Grande Valley.


Yao Xie

Georgia Institute of Technology

Program Committee

  • Dr. Yuxuan Liang, National University of Singapore
  • Mr. Haomin Wen, Beijing Jiao University
  • Dr. Suining He, University of Connecticut
  • Mr. Ming Jin, Monash University
  • Mr. Yushan Jiang, University of Connecticut
  • Dr. Yuncong Chen, NEC Laboratories America, Inc.
  • Dr. Fei Miao, University of Connecticut
  • Mr. Zijie Pan, University of Connecticut
  • Mr. Li Zhang, Georg Mason University
  • Mr. Defu Cao, University of Southern California
  • Mr. Wei Zhu, University of Rochester
  • Dr. Xiang Zhang, UNC Charlotte
  • Dr. Manas Guar, University of Maryland Baltimore County
  • Dr. Feiyang Cai, Stony Brook University
  • Dr Chen Luo, Amazon
  • Dr. Jiechao Gao, University of Virginia
  • Dr. Sahil Garg, Morgan Stanley
  • Dr. Pengyang Wang, University of Macau
  • Dr. Dongsheng Luo, FIU
  • Dr. Azadeh Alavi, RMIT University
  • Dr. Fernando Gama, Morgan Stanley
  • Mr. Chen Xu, Georgia Institute of Technology
  • Dr. Xiao-jun Zeng, University of Manchester
  • Dr. Dongkuan Xu, North Carolina State University