报告题目：Finding Statistical Characteristics and Similarities of Substructures between Knowledge Networks
Prof. Jie Wang
Department of Computer Science
University of Massachusetts, Lowell, MA, USA
报告地点：软件楼 102 室第二会议室
报告时间：3 月 15 日（周四）上午 9：30
Statistical characteristics of knowledge networks may help reveal internal structures of knowledge and how knowledge is evolved and organized. We analyze statistical properties of domain knowledge networks and show the goodness of fit of double Pareto lognormal distribution on node degrees. Finding structural similarities between large inter-domain knowledge networks using computational methods is expected to facilitate the discovery of new knowledge. We devise an efficient algorithm using random walkers and time series to identify structural similarities of sub-networks between inter-domain knowledge networks. Concepts with similar structures identified by the algorithm may indicate unknown relationships between them, which may be worth the effort of domain experts to investigate. Our method can be applied to large knowledge repository such as Wikipedia. In particular, we devise an efficient mechanism to extract domain knowledge networks from Wikipedia, and use it to extract four domain networks, namely, mathematics, physics, biology, and chemistry. We examine these knowledge networks and list concept pairs with high similarity scores. We present strong evidence to some of these pairs that they are indeed related.
This is joint work with Weibo Gong, Zheng Fang, and Benyuan Liu.
Speaker’s Brief Bio
Dr. Jie Wang is Professor and Chair of Computer Science at the University of Massachusetts, Lowell, USA. He is also Director of China Partnerships under Provost, Director of the University Center for Network and Information Security, and co-Director of the University Center for Cyber Forensics. He received his PhD in Computer Science from Boston University in 1991, Master of Engineering in Computer Science from? Zhongshan (Sun Yat-sen) University in 1985, and Bachelor of Science in Computational Mathematics from Zhongshan University in 1982. His research interests include computational complexity theory, modeling and algorithms, network security, and computational medicine. He has worked as a security consultant in financial industry. His recent research focus is on network dynamics, knowledge discovery, and wireless sensor networks. His research has been funded by the NSF since 1991. IBM, Intel, Google and the Natural Science Foundation of China have also funded his research. He has published over 150 research papers in some of the most prestigious journals and conference proceedings. He has authored and co-authored five books; edited and co-edited four books. He is active in professional service, including chairing conference program committees, serving as editor-in-chief or a book series on modeling and algorithms and as journal editors, and organizing conferences and workshops.