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, and key technical issues, and present solutions to tackle related challenges in practical applications. The workshop will focus on both theoretical 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, astronomy, and urban design to 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:
Submissions should be 5-9 pages long, excluding references, and follow SDM 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). We also welcome submissions of unpublished papers, including those that are submitted/accepted to other venues if that other venue allows so.
Any questions may be directed to the workshop e-mail address: Contact Us
Workshop Paper Submission Due Date:March 05, 2024(AoE) March 15, 2024(AoE)
Notification of Paper Acceptance:March 12, 2024(AoE) March 25, 2024(AoE)
Camera-ready Papers Due: April 5, 2025
Workshops Day: May 1st, 2025
Submission link: https://cmt3.research.microsoft.com/AI4TSSDM2025
The 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.
Time(GMT+8) | Title | Speaker |
---|---|---|
10:00 am - 10:05 am | Opening Remarks and Setup for morning talks | |
10:05 am – 10:50 pm | Keynote Talk: Forecasting Societal Disruptions from Social Media Time Series: Models, Systems, and Insights | Dr. Chang-Tien Lu |
10:50 am - 11:35 am | Keynote Talk: Knowledge-Guided Machine Learning for Scientific Discovery: Challenges and Opportunities | Dr. Xiaowei Jia |
11:35 am - 11:50 am | Contributed talk: Building Trust in Machine Learning-Powered Networking: The Network Explainer Framework | |
11:50 am – 12:05 am | Contributed talk: Value and Shape-Aware Transformer for Multivariate Time Series Classification | |
12:05pm – 1: 30 pm | Lunch Break | |
13:30 pm - 14:15 pm | Keynote Talk: From Repetition to Insight: Shaping a More Interpretable Future through Time Series Motif Discovery | Dr. Jessica Lin |
14:15 pm – 14:30 pm | Setup for afternoon talks | |
14:30 pm – 14:45 pm | Contributed talk: Time Series Anomaly Detection with Untrained Convolutional Kernels | |
14:45 pm – 15:00 pm | Contributed talk: Enhancing Self-Supervised Learning Representation Efficiency for Time Series via Similarity-Based Compression | |
15:00 pm – 15:15 pm | Contributed talk: Disentangling Data Availability and Class Variability in Multivariate Time Series for Rare Event Prediction: A GAN-Based Approach to Solar Flare Forecasting | |
15:15 pm – 15:30 pm | Closing remark |
This talk explores how social media time series can be leveraged for the early warning of societal events using the AI-driven forecasting system EMBERS. By modeling temporal patterns in open-source data, augmented by Dynamic Query Expansion (DQE), EMBERS generates real-time predictions of civil unrest with actionable lead times. I will outline its key components, including time-aware event modeling and retrospective evaluation using metrics such as lead time and precision. Case studies from Latin America illustrate how temporal modeling of social signals can yield proactive insights into complex societal dynamics. The second part of the talk introduces SimNest, a deep learning framework that integrates computational epidemiology with social media for real-time flu surveillance. I will also present a multi-task learning approach for spatiotemporal forecasting across regions, designed to address data sparsity and geographic heterogeneity. Together, these approaches demonstrate how AI can effectively model social media time series to enhance crisis anticipation and response.
Data science and machine learning (ML) models, which have found tremendous success in several commercial applications where large-scale data is available, e.g., computer vision and natural language processing, has met with limited success in scientific domains. Traditionally, physics-based models of dynamical systems are often used to study engineering and environmental systems. Despite their extensive use, these models have several well-known limitations due to incomplete or inaccurate representations of the physical processes being modeled. Given rapid data growth due to advances in sensor technologies, there is a tremendous opportunity to systematically advance modeling in these domains by using machine learning methods. However, capturing this opportunity is contingent on a paradigm shift in data-intensive scientific discovery since the “black box” use of ML often leads to serious false discoveries in scientific applications. Because the hypothesis space of scientific applications is often complex and exponentially large, an uninformed data-driven search can easily select a highly complex model that is neither generalizable nor physically interpretable, resulting in the discovery of spurious relationships, predictors, and patterns. This problem becomes worse when there is a scarcity of labeled samples, which is quite common in science and engineering domains. My work aims to build the foundations of knowledge-guided machine learning (KGML) by exploring several ways of bringing scientific knowledge and machine learning models together. In particular, we discuss gaps and opportunities in scientific discovery and show the effectiveness of KGML in multiple applications of great societal and scientific relevance. My work also has the potential to greatly advance the pace of discovery in a number of scientific and engineering disciplines where physics-based models are used, e.g., hydrology, agriculture, climate science, materials science, power engineering and biomedicine.
Massive amounts of data are generated daily at a rapid rate. As a result, the world is faced with unprecedented challenges and opportunities on managing the ever-growing data, and much of the world's supply of data is in the form of time series. In this presentation, I will explore unsupervised pattern discovery in time series data, with a particular emphasis on time series motif discovery. Time series motif discovery involves identifying recurring, similar patterns within a dataset over time. These motifs are essential for summarizing repetitive behaviors, uncovering hidden structures, and revealing meaningful semantics within complex time series data. Beyond their role in providing insight into the data, motifs serve as powerful building blocks for a variety of downstream tasks, such as classification and anomaly detection, and enable us to build more effective, transparent, and interpretable models. In this talk, I will address the foundational challenges that arise in motif discovery. I will also highlight recent advancements that have made significant strides in overcoming these challenges.
* Building Trust in Machine Learning-Powered Networking: The Network Explainer Framework Riya Ponraj, Ram Durairajan, Yu Wang
* Value and Shape-Aware Transformer for Multivariate Time Series Classification Wenjie Xi, Rundong Zuo, Alejandro Alvarez, Jie Zhang, Jessica Lin
* Time Series Anomaly Detection with Untrained Convolutional Kernels Wenjie Xi, Jessica Lin
* Disentangling Data Availability and Class Variability in Multivariate Time Series for Rare Event Prediction: A GAN-Based Approach to Solar Flare Forecasting Junzhi Wen, Rafal A. Angryk
* Enhancing Self-Supervised Learning Representation Efficiency for Time Series via Similarity-Based Compression Brooklyn Berry, Yifeng Gao
Assistant Professor
University of Texas at Rio Grande Valley
Contact: li.zhang@utrgv.edu
Li Zhang is an assistant professor in the Department of Computer Science at University of Texas Rio Grande Valley. Her research focuses on designing reliable time series data mining tools for various tasks including time series forecasting, pattern discovery, anomaly detection, classification. Her work have appeared on top-tier data mining conferences such as ICDM, SDM and CIKM, as well as interdisciplinary applications related to time series including one best student paper runner-up. She has hosted a tutorial on time series pattern mining in SDM24 and organized AI4TS time series workshop in IJCAI 2024. She has served as an associate editor for Big Data Research, and a PC member in major data mining and machine learning conferences such as KDD, SDM, ICDM, Neurips, AAAI, etc. Her research is sponsored by the National Science Foundation.
Dongjin Song is an assistant professor in the Department of Computer Science and Engineering at the University of Connecticut. He has strong expertise in machine learning, deep learning, and related applications for time series data analysis (including representation, prediction, anomaly detection, and diagnosis). Papers describing his research have been published at top-tier data science and artificial intelligence conferences, such as AAAI, IJCAI, NeurIPS, ICML, ICLR, KDD, ICCV, ICDM, SDM, etc. He has served as Senior PC for AAAI, IJCAI, and CIKM. He won the UConn Research Excellence Research (REP) Award in 2021.
Head of AI Research & Chief Scientist
Squirrel AI Learning
Contact: qingsongedu@gmail.com
Qingsong Wen is currently the Head of AI Research & Chief Scientist at Squirrel AI Learning by Yixue Education Inc., working on AI for Education via SOTA technologies (like LLM, AI Agent, GenAI, Transformer, SSL, GNN, etc.). Previously, he worked at Alibaba on AI for Time Series in Cloud Computing, E-Commerce, and Energy Industries, at Qualcomm and Marvell in big data and signal processing. He received his M.S. and Ph.D. degrees in Electrical and Computer Engineering from Georgia Institute of Technology, Atlanta, USA. He has published over 80 top-ranked conference and journal papers, received AAAI/IAAI 2023 Innovative Application Award, and won the First Place in 2022 ICASSP Grand Challenge Competition. He is an Associate Editor for Neurocomputing, Guest Editor for IEEE Internet of Things Journal, Guest Editor for Applied Energy, and regularly served as an Area Chiar/SPC/PC member of the major AI/DM/SP conferences including AAAI, IJCAI, KDD, ICDM, ICASSP, etc.
Shirui Pan is a Professor and an ARC Future Fellow with the School of Information and Communication Technology, Griffith University, Australia. Before joining Griffith in 2022, he is a Senior Member of IEEE and ACM, and a Fellow of Queensland Academy of Arts and Sciences (FQA). His research focuses on artificial intelligence and machine learning. He has made contributions to advance graph machine learning methods for solving hard AI problems for real-life applications, including graph classification, anomaly detection, recommender systems, and multivariate time series forecasting. His research has been published in top conferences and journals including NeurIPS, ICML, KDD, TPAMI, TNNLS, and TKDE. He is recognised as one of the AI 2000 AAAI/IJCAI Most Influential Scholars in Australia (2023, 2022), and one of the World’s Top 2% Scientists (2022, 2021). His research received the 2020 IEEE ICDM Best Student Paper Award (2020), and the 2024 IEEE CIS TNNLS Outstanding Paper Award. He has eight papers recognised as the Most Influential Papers in KDD, IJCAI, AAAI, and CIKM (x1). He received a prestigious Future Fellowship (2022-2025), one of the most competitive grants from the Australian Research Council (ARC).