Home Page
Developing Machine Learning Models to Tackle Hard Data Analytics Problems in Knowledge-Rich Domains
Machine Learning and Data Intensive Computing (Mining)
The Mining Lab aims to build statistical models to tackle hard learning problems with limited labels in knowledge-rich domain (e.g., medicine and bioinformatics).
Two central research themes:
- Developing interpretable machine learning models that analyze large-scale multimodal dynamic data with limited supervised information
- Keeping humans in the loop for interactive and continuous model improvement.
News
- Januray 2025
ICLR 2025 Acceptance
We have two papers accepted by ICLR 2025.
- December 2024
AAAI 2025 Acceptance
We have two papers accepted by AAAI 2025.
- September 2024
NeurIPS 2024 Acceptance
We have FOUR papers accepted by NeurIPS 2024.
- July 2024
KDD 2024 Acceptance
We have a paper accepted by KDD 2024.
Research
Utilizing synergy between human and computer information processing for complex visual information organization and use
NSF IIS Award (~$500K, July 2018- June 2023)
A Multimodal Dynamic Bayesian Learning Framework for Complex Decision-making
DoD/ONR (~$1.6M, October 2018- September 2023)
Using Novel Scientific Machine Learning to Revolutionize Computational Methods for High-Energy-Density Physics
DOE-Department of Energy / University of Rochester
Accurate and Efficient Understanding of Dynamic Materials under Extreme Conditions Through Novel Scientific Machine Learning
Center for Matter at Atomic Pressures (CMAP), University of Rochester
Our People
-
Qi Yu & Xumin Liu (Lab Directors)
-
Ph.D Students
-
MS Students
