********************************************************************

                                                     Seminar

             Department of Systems Engineering and Engineering Management
                                  The Chinese University of Hong Kong

------------------------------------------------------------------------------------------

Title	:	Active Learning with Generalized Queries
Speaker	:	Prof. Charles Ling
		Department of Computer Science
		University of Western Ontario, Canada
Date	:	May 25th, 2010 (Tuesday)
Time	:	4:30 p.m. - 5:30 p.m.
Venue	:	Room 513
		William M.W. Mong Engineering Building
		(Engineering Building Complex Phase 2)
		CUHK

------------------------------------------------------------------------------------------

Abstract:
　

Active learning can actively select or construct examples (queries) and request their labels to reduce the number of labeled examples needed for building an accurate classifier.

However, previous works of active learning can only ask specific queries with all attribute values, many of which may be irrelevant.
A more natural and powerful way is to ask ``generalized queries\'\' with only relevant attributes, such as ``are people over 50 with knee pain likely to have osteoarthritis?\'\' (with only two attributes: age and type of pain while omitting many other irrelevant ones).
The power of asking such generalized queries is that one generalized query may be equivalent to many specific ones.
However, overly general queries may receive uncertain labels from the oracle, and this makes learning difficult.
In this talk I will propose a novel active learning algorithm that asks good generalized queries. We demonstrate experimentally that our new method asks significantly fewer queries compared with the previous works of active learning. Our method can be readily deployed in real-world data mining tasks where obtaining labeled examples is costly.

-------------------------------------------------------------------------------------------

Biography:
　

Charles X. Ling earned his dual-BSc (Computer Science & EE) from Shanghai Jiao Tong University in China. Then he studied in the Department of Computer and Information Science at University of Pennsylvania, and obtained both MSc and PhD within four years. Since then he has been a faculty member in the Department of Computer Science at the University of Western Ontario, Canada. He is currently a Full Professor, and the Director of Data Mining and Business Intelligence Lab. He is IEEE Senior Member.

His main research areas include machine learning (theory, algorithms, and applications), data mining (applications in Custom Relationship Management, Web data, search engine, medical data, and so on), cognitive modeling and child education. He has published over 120 peer-reviewed research papers in journals and international conferences.

He is an Associate Editor for IEEE TKDE (IEEE Transaction on Knowledge
and Data Engineering), ACM Transactions on Intelligent Systems and Technology (ACM TIST), and Computational Intelligence Journal. He has been Conference Chair, PC Chair, Senior PC Member, Area Chair, and Program Committee member for major international conferences on machine learning and data mining.

************************* ALL ARE WELCOME ************************

Host	:	Prof. Lam Wai
Tel	:	(852) 2609-8306
Email	:	wlam@se.cuhk.edu.hk
Enquiries	:	Prof. Nan Chen or Prof. Sean X. Zhou
	:	Department of Systems Engineering and Engineering Management
		CUHK
Website	:	http://www.se.cuhk.edu.hk/~seg5810
Email	:	seg5810@se.cuhk.edu.hk

********************************************************************