Qi, Yanjun
Primary Appointment
Associate Professor, Computer Science
Education
- B.S., Computer Science, Tsinghua University, Beijing
- Ph.D., Computer Science, Carnegie Mellon University
Contact Information
Rice Hall, Room 503
Telephone: 434-243-3089
Email: yq2h@virginia.edu
Research Interests
“Machine Learning for Big Data Analytics In Biomedicine"
Research Description
UVA "Machine Learning and Bioinformatics" group's research has been focused on developing and applying machine-learning techniques on important challenges in biomedicine, especially those dealing with enormous data sets. Taking an inter-disciplinary approach, we have devoted our research efforts on both the improvement of machine learning technologies and the advancement of biomedical research.
Combining ideas from statistical machine learning, computational biology and language technologies, we have published across a wide range of conferences and journals, including bioinformatics, machine learning, statistical data mining, and information retrieval. We strive toward building and sharing benchmarked datasets and open-source releases of research prototypes.
Machine Learning and Data Mining
Rapidly-growing biomedical data resources have posted many interesting new challenges for machine learning, with the data being large, loosely labeled, highly diverse, complex and often relationally structured. We have proposed a diverse range of machine learning approaches, including semi-supervised learning, multi-task learning, feature learning, deep learning, sparse modeling, latent factor analysis, learning to rank, and etc, to handle different types of data complexities that are urgent to be addressed in this domain.
Bioinformatics and Biomedical Informatics
Given the inter-disciplinary nature, my group has had valuable opportunities to work on many practically important applications, covering multiple research fields, such as proteomics, cancer genomics, medical informatics, bio-text mining, structural biology, immunology, and more traditional text mining topics, like information extraction, ad hoc information retrieval and text/image/video labeling.