IJCAI'22 Workshop




AI4TS: AI for Time Series


Analysis:




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 some 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 issues in practical applications. The workshop will focus on both the theoretical and practical aspects of time series data analysis and aims to trigger research innovations on 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 prediction
  • Classification and clustering
  • Anomaly detection and diagnosis/change point detection
  • Similarity search
  • Time series indexing
  • Pattern discovery
  • Interpretation and explanation
  • Bias and fairness
  • Causal inference
  • Spatio-temporal prediction
  • Predictive maintenance
  • Healthcare
  • Fintech
  • Traffic analysis
  • Weather forecasting
  • Internet of things
  • Machine learning
  • Data Mining
  • Artificial Intelligence
  • AI-inspired approaches for time series similarity search
  • Experimental evaluation and comparison of AI and traditional techniques
  • New benchmarks for time series analysis tasks

Call for Papers

Submissions should be 4-6 pages long, excluding references, and follow IJCAI-22 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 posted on the workshop webpage. We 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/AI4TS2022/

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

Key Dates

 

Workshop Paper Submission Due Date: May 13, 2022

Notification of Paper Acceptance: June 3, 2022

Camera-ready Papers Due: June 17, 2022

IJCAI-21 Workshops: July 24, 2022

Schedule

9:00 AM - 4:10 PM, July 24th,2022, CEST/Vienna time


Location: Messe Wien Exhibition and Congress Center (Schubert 4)


Zoom Link: https://uni-sydney.zoom.us/j/86982872150

Time(UTC+2)SpeakerTitle
9:00 am - 9:10 amDr. Hangwei QianOpening remarks
9:10 am - 10:00 amDr. Haifeng ChenSignals, Structure, and Dynamics: Unraveling the Unknown in Complex Systems
10:00 am - 10:45 amPaper presentation 1-4

RADNET: Incident Prediction in Spatio-Temporal Road Graph Networks Using Traffic Forecasting

Expressing Multivariate Time Series as Graphs with Time Series Attention Transformer

HiMLEdge-An Energy-Aware Optimization Framework for Hierarchical Machine Learning in Wireless Sensor Systems at the Edge

LETS-GZSL: A Latent Embedding Model for Time Series Generalized Zero Shot Learning

10:45 am - 11:15 amCoffee break 
11:15 am - 12:05 pmDr. Jan GasthausProbabilistic Time Series Forecasting: Past, Present, and Future
12:05 pm - 12:30 pmPaper presentation 5-6

Incremental Stock Volume Prediction with Gradient Distillation and Diversified Memory Selection

Towards Safe Autonomy in Hybrid Traffic: The Power of Information Sharing in Detecting Abnormal Human Drivers Behaviors

12:30 pm - 2:00 pmLunch 
2:00 pm - 3:00 pmDr. Kashif RasulTransformers for Time Series Forecasting
3:00 pm - 3:30 pmCoffee Break 
3:30 pm - 4:06 pmPaper presentation 7-9

Deep-Learning vs Regression: Prediction of Tourism Flow with Limited Data

DTG-LSTM: A Delaunay Triangulation Graph for Human Trajectory Prediction in Crowd Scenes

A Wavelet Decomposition based Ensemble Learning Framework for Short-Term Stock Prediction

4:06 am - 4:10 pmDr. Haifeng ChenClosing remarks
 

Speakers

Haifeng Chen

Dr. Haifeng Chen

Department Head of Data Science
NEC Labs America

Dr. Haifeng Chen, NEC Labs America

Dr. Haifeng Chen is heading the Data Science and System Security Department at NEC Laboratories America in Princeton, New Jersey. He received the BEng and MEng degrees in automation from Southeast University China, and the PhD degree in computer engineering from Rutgers University in 2004. He and his team members are working on various topics related to big data analytics, AI, software and system security, smart service and platforms. Dr. Chen has served in the program committee for a number of top AI conferences, and has been in the panel of National Science Foundation (NSF) programs. He is a member of the school of Systems and Enterprises Advisory Board in Stevens Institute of technology, New Jersey. Dr. Chen has co-authored more than a hundred conference/journal publications including the best paper runner-up at SigKDD’16, and has over 70 patents granted. Most of his research led to advanced solutions and products for various industrial domains including power plants, satellite, financial, retail, and so on.

Jan Gasthaus

Dr. Jan Gasthaus

Amazon Web Services
AWS AI Labs

Dr. Jan Gasthaus, Amazon Web Services, AWS AI Labs

Dr. Jan GasthausJan Gasthaus is a Principal Machine Learning Scientist in the Amazon AI Labs, working mainly on time series forecasting, anomaly detection, and large-scale probabilistic machine learning. He is passionate about developing novel machine learning solutions for addressing challenging business problems with scalable machine learning systems, all the way from scientific ideation to productization. Prior to joining Amazon, Jan obtained a BS in Cognitive Science from the University of Osnabrueck, an MS in Intelligent Systems from UCL, and a PhD from the Gatsby Unit, UCL, focusing on Nonparametric Bayesian methods for sequence data.

Kashif Rasul

Dr. Kashif Rasul

Morgan Stanley

Dr. Kashif Rasul, Morgan Stanley

Dr. Kashif Rasul is a Research Scientist at Morgan Stanley where he works on deep learning based time-series forecasting problems. He also contributes to open source machine learning software. He studied Mathematics at Monash University in Australia and obtained his PhD from the Free University in Berlin, Germany.

Accepted Papers

 

* RADNET: Incident Prediction in Spatio-Temporal Road Graph Networks Using Traffic Forecasting
 Shreshth Tuli, Matthew R. Wilkinson and Chris Kettell.

* Expressing Multivariate Time Series as Graphs with Time Series Attention Transformer
 William T. Ng, K. Siu, Albert C. Cheung and Michael K. Ng.

* HiMLEdge-An Energy-Aware Optimization Framework for Hierarchical Machine Learning in Wireless Sensor Systems at the Edge
 Julio Wissing, Stephan Scheele, Aliya Mohammed, Dorothea Kolossa and Ute Schmid.

* LETS-GZSL: A Latent Embedding Model for Time Series Generalized Zero Shot Learning
  Sathvik Bhaskarpandit,Priyanka Gupta and Manik Gupta.

* Incremental Stock Volume Prediction with Gradient Distillation and Diversified Memory Selection
  Shicheng Li, Zhiyuan Zhang, Lei Li, Ruihan Bao, Keiko Harimoto and Xu Sun.

* Towards Safe Autonomy in Hybrid Traffic: The Power of Information Sharing in Detecting Abnormal Human Drivers Behaviors
 Jiangwei Wang, Lili Su, Songyang Han, Dongjin Song and Fei Miao.

* Deep-Learning vs Regression: Prediction of Tourism Flow with Limited Data
 Julian Lemmel, Zahra Babaiee, Marvin Kleinlehner, Ivan Majic, Philipp Neubauer, Johannes Scholz, Radu Grosu and Sophie A. (Gruenbacher) Neubauer.

* DTG-LSTM: A Delaunay Triangulation Graph for Human Trajectory Prediction in Crowd Scenes
 Zhimiao Shi and Yao Xiao.

* A Wavelet Decomposition based Ensemble Learning Framework for Short-Term Stock Prediction
 Hieu Nguyen, Jihye Moon, Dongjin Song and Joseph Johnson.

 

Workshop Organizers

The following are arranged in alphabetical order

 

Dongjin Song

Assistant Professor, University of Connecticut

 

Fenglong Ma

Assistant Professor
Pennsylvania State University

 

Sanjay Purushotham

Assistant professor
University of Maryland Baltimore County

 
 

Themis Palpanas

Senior Member
the French University Institute (IUF)

 

Wei Cheng

Senior Researcher
NEC Labs America

 

Yifeng Gao

Assistant Professor
University of Texas Rio Grande Valley.

 
 
 

Yufei Han

Senior Research Scientist
INRIA France

 

Program Committee

  • Dr. Abhishek Mukherji, Accenture Inc
  • Dr. Chen Luo, Amazon
  • Dr. Chuxu Zhang, Brandeis University
  • Dr. Derek Aguiar, University of Connecticut
  • Dr. Jiayu Zhou, Michigan State University
  • Dr. Jingchao Ni, NEC Laboratories America, Inc.
  • Dr. John Paparrizos, University of Chicago
  • Dr. Paul Boniol, Université de Paris
  • Dr. Qingsong Wen, Alibaba DAMO Academy
  • Dr. Shuochao Yao, George Mason University
  • Dr. Suining He, University of Connecticut
  • Dr. Wei Zhu, University of Rochester
  • Dr. Yuncong Chen, NEC Laboratories America, Inc.
  • Dr. Xingjian Shi, HKUST
  • Mr. Yushan Jiang, University of Connecticut
  • Dr. Zhengping Che, Midea Group
  • Dr. Zhengzhang Chen, NEC Laboratories America, Inc.