Beyond connecting the dots: network clustering algorithms and their applications

Abstract

Big data is highly complex with many interrelated elements, which can be modeled as a network by connecting the dots (i.e. the interrelated elements). The network provides us a big picture of the underlying complexity, but it is often too big to discover any useful hidden patterns from millions of nodes and links. This talk first presents the clustering algorithms for large networks, which can efficiently detect different hidden patterns including community structures (which refer to the occurrence of groups of nodes in a network that are more densely connected internally than with the rest of the network), and nodes playing special roles such as outliers or hubs, as well as different types of relationships. Another focus of this talk is about the application of the network clustering algorithms to different networks including social networks, biological networks, as well as to entity co-occurrence network for text mining. The talk is for general audients with diverse background and interest.

Biography

Xiaowei Xu, a professor of Information Science at the University of Arkansas at Little Rock (UALR), received his Ph.D. degree in Computer Science at the University of Munich in 1998. Before his appointment in UALR, he was a senior research scientist in Siemens, Munich, Germany. His research spans data mining, machine learning, bioinformatics, database management systems and high-performance computing. He has published over 100 papers in peer-reviewed journals and conference proceedings. With over 17,864 citations, he is one of the most cited researchers according to Google Scholar. His groundbreaking work on the density-based clustering algorithm DBSCAN has been widely used in textbooks and software implementations; and has received over 11,506 citations based on Google scholar to date. He is recipient of the prestigious ACM SIGKDD Test of Time award for his contribution to the density based clustering algorithm DBSCAN.