Wenyuan Dai

Biography

I am a master candidate in the APEX Data & Knowledge Management Lab of the Department of Computer Science and Engineering (CSE), Shanghai Jiao Tong University (SJTU). My supervisor is Professor Yong Yu.

During September to November 2006, I was a visiting postgraduate student in Hong Kong University of Science and Technology, supervised by Professor Qiang Yang.

I was a member of the SJTU programming contest team, and competed in the 29th Annual ACM International Collegiate Programming Contest (ACM-ICPC). Our team won the World Champions in this contest. Moreover, I was granted the University President's Award when I was a junior student, and was granted the National Honor Student Award when I was a senior student.

Research Interests

My research interests focus on several areas related to Machine Learning:

• Transfer Learning: Compared with human learning, machine learning lacks the ability to inherit the knowledge learnt in the past, especially for the knowledge in a different domain than the target domain. One example is learning physic relies on fundamental knowledge in mathematics. In this situation, different learning processes are isolated within different learning scenarios. This is a main reason that machine learning cannot catch the strength of human learning. To broaden the generality of machine learning, transfer learning is proposed to build connections between different learning processes, and let the learnt knowledge be better utilized for further learning. My recent work mainly focuses on

  • Cross-domain Learning: Learning when training and test data come from different domains

  • Unsupervised Transfer Learning: Transfer learning for clustering, feature selection, summarization, and so on

• Computational Cognitive Science: One of the most importance issues in artificial intelligence is to understand and model human intelligent behaviors. In my opinion, AI can be developed in a bionic way. Computational cognitive science is to model the human cognition in computational terms, and thus could be much helpful for improving AI techniques.

• Large Scale Machine Learning: One of the bottlenecks of most machine learning algorithms is the lack of efficiency. Therefore, improving the scalablity of machine learning algorithms can definitely increase their applicability in practice.

I am also interested in applying my machine learning research to real-world applications in Web Search, Data Mining, Computer Vision, etc.

Education

• Master Candidate (September 2006 - Present):

  • Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China.

  • Advisor: Yong Yu & Gui-Rong Xue

• Visiting Postgraduate Student (September 2006 - November 2006):

  • Computer Science and Engineering, Hong Kong University of Science and Technology, Kowloon, Hong Kong.

  • Advisor: Qiang Yang

• Bachelor (September 2002 - June 2006):

  • Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China.

  • Bachelor thesis: Personalized Email Spamming Detection (in Chinese)

Selected Publications

2008:

• Xiao Ling, Wenyuan Dai, Gui-Rong Xue, Qiang Yang, and Yong Yu. Spectral Domain-Transfer Learning. To appear in Proceedings of the Fourteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2008), Las Vegas, Nevada, USA, August 24-27, 2008.

• Gui-Rong Xue, Wenyuan Dai, Qiang Yang and Yong Yu. Topic-bridged PLSA for Cross-Domain Text Classification. In Proceedings of the Thirty-first International ACM SIGIR Conference on Research and Development on Information Retrieval (SIGIR 2008), Pages 627-634, Singapore, July 20-24, 2008. (slides)

• Wenyuan Dai, Qiang Yang, Gui-Rong Xue and Yong Yu. Self-taught Clustering. In Proceedings of the Twenty-Fifth International Conference on Machine Learning (ICML 2008), Pages 200-207, Helsinki, Finland, 5-9 July, 2008. (slides)

• Xiao Ling, Gui-Rong Xue, Wenyuan Dai, Yun Jiang, Qiang Yang and Yong Yu. Can Chinese Web Pages be Classified with English Data Source? In Proceedings the Seventeenth International World Wide Web Conference (WWW 2008), Pages 969-978, Beijing, China, April 21-25, 2008.

2007:

• Dikan Xing, Wenyuan Dai, Gui-Rong Xue and Yong Yu. Bridged Refinement for Transfer Learning. In Proceedings of the Eleventh European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD 2007), Pages 324-335, Warsaw, Poland, September 17-21, 2007. Best Student Paper Award (slides, presentation)

• Wenyuan Dai, Gui-Rong Xue, Qiang Yang and Yong Yu. Co-clustering based Classification for Out-of-domain Documents. In Proceedings of the Thirteenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2007), Pages 210-219, San Jose, California, USA, Aug 12-15, 2007. (slides)

• Wenyuan Dai, Gui-Rong Xue, Qiang Yang and Yong Yu. Transferring Naive Bayes Classifiers for Text Classification. In Proceedings of the Twenty-Second National Conference on Artificial Intelligence (AAAI 2007), Pages 540-545, Vancouver, British Columbia, Canada, July 22-26, 2007. (slides)

• Wenyuan Dai, Qiang Yang, Gui-Rong Xue and Yong Yu. Boosting for Transfer Learning. In Proceedings of the Twenty-Fourth International Conference on Machine Learning (ICML 2007), Pages 193-200, Corvallis, Oregon, USA, June 20-24, 2007. (slides)

See full publication list.

Professional Activities

• Reviewer

  • IEEE Transactions on Knowledge and Data Engineering (TKDE)

Data Sets

• Domain-Transfer Learning Data Sets (readme, download)

Selected Honors

• The 2007 European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD 2007): Best Student Paper Award

• The 2006 ACM International Collegiate Programming Contest - World Finals: 5th Place, Silver Medal & Asia Champions (as an assistant coach)

• The 2006 National Youth Innovation Award in Science and Technology (100 all over China)

• The 2006 National Honor Student Award (10 all over China)

• The 2005 ACM Asia Programming Contest - Tokyo: Champions (as an assistant coach)

• The 2005 President's Award, Shanghai Jiao Tong University

• The 2005 ACM International Collegiate Programming Contest - World Finals: World Champions, Gold Medal & Asia Champions

• The 2004 ACM Asia Programming Contest - Ehime: Champions

• The 2004 ACM Asia Programming Contest - Taipei: Champions

• The 2003 ACM Asia Programming Contest - Beijing: Champions

• The 2002 USACO US Open Contest, Non-USA Green (Senior) Division: 1st Place

• The 2002 USACO Spring Open Contest, Green (Senior) Division: 1st Place

See full honor list.

Experiences

• Research Intern

  • Apex Data & Knowledge Management Lab (May 2005 - June 2006)

    • Worked on Large Scale Web and Data Mining.

  • Department of Computer Science and Engineering, Hong Kong University of Science and Technology (September 2007 - November 2007)

    • Worked on Transfer Learning.

• Teaching Assistant

  • Introduction to Programming, Fall 2005

• Assistant Coach

  • The SJTU International Collegiate Programming Contest Team (May 2005 - present)

• Volunteer
  • The Twenty-Fourth International Conference on Machine Learning (ICML 2007), Corvallis, Oregon, USA, June 20-24, 2007.
  • The Twenty-Second National Conference on Artificial Intelligence (AAAI 2007), Vancouver, British Columbia, Canada, July 22-26, 2007.
  • The Seventeenth International World Wide Web Conference (WWW 2008), Beijing, China, April 21-25, 2008.
  • The Twenty-Fifth International Conference on Machine Learning (ICML 2008), Helsinki, Finland, July 5-9, 2008.

This page has been visited 6554 times since September 15, 2006.