Faculty profile

Xiaojin Zhu

Xiaojin Zhu

Dept. of Computer Sciences
4369 Computer Sciences and Statistics
(608) 890-0129

Links: Department

Research Keywords

computer science, statistical machine learning, semi-supervised learning, natural language processing


  • Department of Computer Sciences, Assistant Professor

Current Projects

  • Statistical Machine Learning from Labeled and Unlabeled Data
  • Text-to-Picture Synthesis for Human Computer Communication

Research Collaborators

Representative Classes

  • Comp Sci 838: Advanced Natural Language Processing
  • Comp Sci 540: Introduction to Artificial Intelligence

Research Statement

I am broadly interested in statistical machine learning, a discipline which studies computer algorithms and statistical models that enable computers to learn from experience. In particular, I am interested in the setting where both labeled and unlabeled examples are available to the learner, also known as semi-supervised learning. The goal is to learn better than only using the labeled data, which is what traditional learning models do. Recently it has become apparent that semi-supervised learning is an important part of human learning. My goal is to better understand the human aspect of learning, and use it as inspiration to develop advanced machine learning models.

My research collaborations focus on novel machine learning applications, and span several disciplines. Some projects include: semi-supervised learning behaviors in human, with Tim Rogers (Psychology) and Chuck Kalish (Ed Psych); text-to-picture synthesis for children's reading comprehension, with Arthur Glenberg (Psychology) and Chuck Dyer (Computer Sciences); statistical software debugging and analysis, with Ben Liblit and Bart Miller (Computer Sciences); recovering text from word counts, with Rob Nowak (ECE); carbon star identification, with Ed Churchwell (Astronomy).

Selected Publications

  • Xiaojin Zhu, Timothy Rogers, Ruichen Qian, and Chuck Kalish. Humans perform semi-supervised classification too. In Twenty-Second AAAI Conference on Artificial Intelligence (AAAI-07), 2007.
  • Xiaojin Zhu, Andrew Goldberg, Mohamed Eldawy, Charles Dyer, and Bradley Strock. A text-to-picture synthesis system for augmenting communication. In The Integrated Intelligence Track of the Twenty-Second AAAI Conference on Artificial Intelligence (AAAI-07), 2007.
  • Xiaojin Zhu and Andrew Goldberg. Kernel regression with order preferences. In Twenty-Second AAAI Conference on Artificial Intelligence (AAAI-07), 2007.
  • Andrew Goldberg, Xiaojin Zhu, and Stephen Wright. Dissimilarity in graph-based semi-supervised classification. In Eleventh International Conference on Artificial Intelligence and Statistics (AISTATS), 2007.
  • Xiaojin Zhu, Andrew Goldberg, Jurgen Van Gael, and David Andrzejewski. Improving diversity in ranking using absorbing random walks. In Human Language Technologies: The Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT), 2007.