Full Contact Information of Organizers
-
Jihoon Chung, Assistant Professor, Hanyang University, Korea, chungjh@hanyang.ac.kr
-
Chenang Liu, Assistant Professor, Oklahoma State University, chenang.liu@okstate.edu
-
Yao Ma Assistant Professor, Rensselaer Polytechnic Institute, may13@rpi.edu
-
Diane Oyen, Scientist and Team Leader of Machine Learning, Los Alamos National Laboratory, doyen@lanl.gov
-
Yinan Wang Assistant Professor, Rensselaer Polytechnic Institute, wangy88@rpi.edu
Workshop Description
In the era of the Internet of Things (IoT), with the rapid development of advanced sensing, data storage, data analytics, and high-performance computing technologies, both manufacturing industries and healthcare systems are experiencing a data‑driven revolution. However, the unique characteristics of manufacturing and healthcare systems prevent the direct application of existing data-driven methods. Their characteristics include (1) systematic physical principles, (2) high demand for interpretability, robustness, and trustworthiness, and (3) limited computation resources and the need for instant decision-making. These characteristics raised pressing needs to develop domain-aware data-driven approaches for critical tasks in manufacturing and healthcare systems, such as smart diagnosis, automatic control, design optimization, customized analytics, etc.
This workshop aims to demonstrate the recent progress of data science research, which focuses on addressing the unique challenges in manufacturing and healthcare systems, such as the gaps in data quality/security assurance, domain-aware data analytics, improvement of trustworthiness, etc. We cordially invite submissions that focus on recent advances in research/development of data science, which are motivated by real-world problems in manufacturing and healthcare. Papers and/or posters focus on both theoretical foundations and applications are welcomed from the areas including but not limited to:
Topics of Interest
Methodology
- Active learning
- Bayesian optimization
- Contrastive learning
- Data-driven inverse modeling
- Deep reinforcement learning
- Domain-aware machine learning
- Generative model
- Graph machine learning
- Image/video processing
- Incremental learning
- Surrogate modeling
- Trustworthy machine learning
- Uncertainty quantification
Application
- Additive manufacturing
- Anomaly detection
- Biomanufacturing
- Cyber-physical systems
- Dataset design
- Data quality and security
- Design optimization
- Disease screening and prediction
- Material/process degradation
- Healthcare and biomedical data analytics
- Imaging and sensing
- Process monitoring and control
- Quality control
- Root cause diagnosis
- Sustainable manufacturing
Keynote Speakers
- Title: Data Mining Electronic Health Records to Combat Healthcare-Associated Infections
Speaker: Dr. Bijaya Adhikari, Assistant Professor, University of Iowa
Abstract: As patients admitted to hospitals seek care, they are simultaneously being exposed to several Healthcare-Associated Infections (HAIs), which lead to increased morbidity and mortality and pose significant financial strains. Fortunately, early detection coupled with effective preventative measures can help mitigate both the health and economic risks of future outbreaks.
The widespread adoption of automated and integrated computing systems in healthcare facilities has led to the availability of fine-grained data, including electronic health records, healthcare provider mobility, clinical notes, and laboratory records. These fine-grained data capture HAI risk and potential pathways of infection, paving the way for data mining and artificial intelligence algorithms to enable effective HAI surveillance and intervention. This talk focuses on recent advances in data-driven algorithms specifically designed to combat HAI.
- Title: Physics-constrained Modeling and Optimization of Complex Systems: Healthcare Application
Speaker: Dr. Jianxin Xie, Assistant Professor, University of Virginia
Abstract: Rapid advances in sensing and imaging techniques have created a data-rich environment and tremendously benefited data-driven predictive modeling and decision-making for complex systems. Realizing the full potential of the sensing and imaging data depends on the development of novel and reliable analytical models and tools for system informatics. The goal of my research is to develop innovative physics-augmented methodologies for modeling, monitoring, and optimizing complex systems. In this talk, I will present two topics to tackle the challenges in complex systems modeling and optimization. In the first topic, a physics-constrained deep learning method is developed to model the spatiotemporal inverse systems. This method integrates physics-based principles with spatiotemporal local support into the advanced deep learning infrastructure to predict the spatiotemporal system dynamics based on indirect and noisy sensor observations. This methodology is implemented in inverse electrocardiography (ECG) modeling, which generates a robust prediction of electrical potential mappings on the heart surface based on body-surface sensor measurements. In the second topic, a novel physics-augmented strategy is proposed for optimal sensor placement to actively explore and model the dynamics of 3D complex-structured systems. This active learning scheme not only combines uncertainty estimation and space-filling design over the complex geometry but also respects the underlying physics-based prior knowledge, enabling effective learning of system dynamics from limited sensor exploration. The framework was implemented to estimate the electrodynamics in both healthy and diseased 3D cardiac systems. The proposed frameworks have profound potential in modeling other spatiotemporal multi-sensor systems.
- Title: Towards Effective and Efficient Multi-Agent Language Model Systems
Speaker: Dr. Xuan Wang, Assistant Professor, Virginia Tech
Abstract: Large language models (LLMs) have shown impressive capabilities in reasoning and planning, making them powerful tools for multi-agent collaboration in complex decision-making. However, current multi-agent LLM systems often struggle with inefficiencies and suboptimal effectiveness. In this talk, I will present our recent research addressing these challenges through graph and prompt optimization techniques designed to improve coordination and reasoning in LLM-based multi-agent systems. I will also introduce our recent work on small language model (SLM)-based multi-agent systems, which aim to deliver competitive performance with significantly greater efficiency. Our frameworks are designed to enhance reasoning robustness, reduce sycophancy, and support real-world adaptability, moving toward more effective and efficient multi-agent language model systems for practical applications.
- Title: Unifying and Optimizing Data Values for Selection via Sequential-Decision-Making
Speaker: Hongliang Chi, Ph.D. Candidate, Rensselaer Polytechnic Insitute
Abstract: Data selection has emerged as a crucial downstream application of data valuation. While existing methods have shown promise, the theoretical foundations of using data values for selection remain largely unexplored. In this talk, I will demonstrate how data values applied for selection can be naturally reformulated as a sequential-decision-making problem where optimal data values are derived through dynamic programming. I’ll show how this framework unifies existing methods like Data Shapley through approximate dynamic programming and analyze performance limitations when utility functions exhibit varying degrees of submodularity. Additionally, I’ll present an efficient approximation scheme using learned bipartite graphs that ensures near-optimal selection while preserving theoretical guarantees.
Description of the Workshop:
This workshop is expected to be a full-day event with two half-day sessions, split by a lunch break. The format of this workshop will include invited keynote presentations and accepted presentations from submitted papers. The tentative workshop agenda is shown as follows.
Tentative Workshop Agenda
Morning Session
- 10:00 – 10:05 Welcome and Opening Remarks
- 10:05 – 10:55 Keynote presentation 1
- Dr. Bijaya Adhikari, University of Iowa, Data Mining Electronic Health Records to Combat Healthcare-Associated Infections
- 10:55 – 11:45 Keynote presentation 2
- Dr. Jianxin Xie, University of Virginia, Physics-constrained Modeling and Optimization of Complex Systems: Healthcare Application
- 11:45 - 12:05 Contributing paper presentation 1
- Jiayu Liu, Rensselaer Polytechnic Institute, Quantum Bayesian Optimization for Quality Improvement in Fuselage Assembly
Lunch Break (12:05 – 13:20)
Afternoon Session
- 13:30 - 14:20 Keynote presentation 3
- Dr. Xuan Wang, Virgnia Tech, Towards Effective and Efficient Multi-Agent Language Model Systems
- 14:20 - 15:10 Keynote presentation 4
- Hongliang Chi, Rensselaer Polytechnic Institute Unifying and Optimizing Data Values for Selection via Sequential-Decision-Making
- 15:10 - 15:15 Closing Remarks
*The schedule may be subject to change according to the SDM conference schedule.
Important Dates
- Travel Award Application: Jan. 30, 2025; link
- Paper Submission: March 21, 2025; Link
- Acceptance Notification: March 28, 2025
- Final Paper Submission: April 6, 2025
Biography of the organizers:
-
Jihoon Chung is an Assistant Professor in the Department of Industrial Engineering at Pusan National University in Korea. He received his Ph.D. degree in Industrial and Systems Engineering at Virginia Polytechnic Institute and State University (Virginia Tech) (May 2023). He also obtained M.S. and B.S. degrees in Industrial Engineering at the Korea Advanced Institute of Science and Technology (KAIST) and Hanyang University, respectively. His research area is developing data-driven methods, including artificial intelligence, machine learning, and statistical learning, to achieve quality assurance in advanced manufacturing processes and solve various problems in healthcare systems and material analysis. His research was recognized as several best paper/poster awards in IISE Quality Control & Reliability Engineering division and INFORMS Quality, Statistics, and Reliability section.
-
Chenang Liu is an Assistant Professor in the School of Industrial Engineering and Management at Oklahoma State University. He earned his Ph.D. degree in Industrial and Systems Engineering from Virginia Tech in 2019. He also received his master’s degree in Statistics from Virginia Tech in 2017 and double bachelor’s degrees from Zhejiang University in 2014. His research interests include data-driven analytics, process quality monitoring and control methodologies, and artificial intelligence-enabled techniques for smart manufacturing, healthcare, and service system applications. His research contributions were recognized by multiple best paper/poster awards. His ongoing research projects are also funded by the federal agencies including NSF, NIH, and FDA, as well as the Oklahoma Center for the Advancement of Science and Technology (OCAST). He is an associate editor of the Journal of Intelligent Manufacturing (JIM), a guest editor of the ASME Journal of Computing and Information Science in Engineering (JCISE), and an executive guest editor of the Journal of Manufacturing Systems (JMS). He was the organizer of 2022 IISE South Central Regional Conference, and he also served as the co-chair of the Data Analytics and Information Systems (DAIS) track in 2023 IISE Annual Conference.
-
Yao Ma is an Assistant Professor in the Department of Computer Science at the Rensselaer Polytechnic Institute (RPI). He received his Ph.D. in Computer Science from Michigan State University (MSU) in 2021, with a focus on machine learning with graph-structured data. His research contributions to this area have led to numerous innovative works presented at top-tier conferences such as KDD, WWW, WSDM, ICLR, NeurIPS, and ICML. He has also organized and presented several well-received tutorials at AAAI and KDD, attracting over 1000 attendees. He is the author of the book “Deep Learning on Graphs”, which has been downloaded tens of thousands of times from over 100 countries. He was awarded the Outstanding Graduate Student Award (2019-2020) from the College of Engineering at MSU.
-
Diane Oyen, Scientist and Team Leader of Machine Learning, Los Alamos National Laboratory. She received her Ph.D. in Computer Science at the University of New Mexico and her B.S. in Electrical Engineering from Carnegie Mellon. She joined Los Alamos National Laboratory in 2013, leading projects on trustworthy machine learning and on computer vision for scientific imagery, involving over a dozen research scientists plus postdocs and students. Her research focuses on developing data science approaches for scientific and national security applications; particularly through the use of graph-based machine learning to understand complex patterns in data. She has organized workshops at top-tier computer vision and machine learning conferences including SDM, CVPR, ECCV, and NeurIPS.
-
Yinan Wang is an Assistant Professor in the Department of Industrial and Systems Engineering at Rensselaer Polytechnic Institute. He received the B.S. degree in Electrical Engineering and Automation from Xi’an Jiaotong University in 2017, the M.S. in Electrical Engineering from Columbia University in 2019, and the Ph.D. in industrial and Systems Engineering from Virginia Tech in 2022. His research interests include data analytics and machine learning techniques in quality control of advanced manufacturing systems. He is the recipient of FTC Early Career Award, 10 Best Paper/Poster/Featured Article Awards, and two Best Ph.D. Dissertation Awards. He was the Mary and Joseph Natrella Scholar from ASA. He is a guest editor of the ASME Journal of Computing and Information Science in Engineering (JCISE) and the co-chair of the Data Analytics and Information Systems (DAIS) track at the 2025 IISE Annual Conference. He was co-organizer for the Symposium in Manufacturing Science and Engineering Conference (MSEC) 2023 and workshops at SIAM International Conference on Data Mining (SDM) 2023 and 2024. He serves as an active Board Director in IISE Data Analytics and Information Systems (DAIS) division.
Previous workshop
For questions regarding this workshop, please contact us at: wangy88@rpi.edu