:irwinking07-1.jpg

Techniques for Multi-Domain Data Analytics

Irwin King

Department of Computer Science and Engineering
The Chinese University of Hong Kong

Abstract

With the development of new applications in web and social networks, data from multiple domains are available for researchers to extract the underlying knowledge. These data contain the characteristics such as large volume, noisy, redundant, heterogeneous, scarce for each individual task. Focusing on the unique characteristics of multi-domain data, we will present three pieces of our work which are promising: 1) Multi-task one class classification, an effective outlier detection method to exclude noisy data with the help of multiple related tasks; 2) Online learning for multi-task feature selection, a scalable feature selection method utilizing the knowledge among multiple related tasks; and 3) Sparse generalized multiple kernel learning, a more accurate data similarity measurement possible for heterogeneous data.

Research Interests

Irwin King's research interests include social computing, machine learning, web intelligence, and multimedia processing. In these research areas, he has over 200 technical publications in journals, conferences, book chapters, and edited volumes. He was the General Chair of Web Search and Data Mining (WSDM2011), and also has been involved with the organization and/or technical program of many international conferences such as WWW, SIGIR, KDD, AAAI, etc. Moreover, he has served as reviewer and panel member for Research Grants Council (RGC) of Hong Kong, Natural Sciences and Engineering Research Council of Canada (NSERC), National Natural Science Foundation of China (NSFC), and Natural Science, and Engineering of Academy of Finland. Dr. King is an Associate Editor of ACM Transactions on Knowledge Discovery from Data (ACM TKDD) and a former Associate Editor of the IEEE Transactions on Neural Networks (TNN). He is a member of the Editorial Board and Special Issue Editor of a number of international journals. He is Professor at the Department of Computer Science and Engineering, The Chinese University of Hong Kong. Currently he is on leave with AT&T Labs Research, San Francisco and is also teaching Social Computing and Data Mining as a Visiting Professor at UC Berkeley. He received his B.Sc. degree in Engineering and Applied Science from California Institute of Technology, Pasadena and both his M.Sc. and Ph.D. degrees in Computer Science from the University of Southern California, Los Angeles. See http://irwinking.com for more information.

Presentation Materials

 
confs/kdd2012workshop.txt · Last modified: 2012/07/07 03:27 by admin     Back to top