Reconstruction from Randomized Graph via Low Rank Approximation¶
Xintao Wu
Associate Professor
Software and Information Systems Department at UNC Charlotte
Abstract :
The privacy concerns associated with data analysis over social networks have spurred recent research on privacy-preserving social network analysis, particularly on privacy-preserving publishing of social network data. In this talk, we focus on whether we can reconstruct a graph from the edge randomized graph such that accurate feature values can be recovered. In particular, we present a low rank approximation based reconstruction algorithm. We exploit spectral properties of the graph data and show why noise could be separated from the perturbed graph using low rank approximation. We also show key differences from previous findings of point-wise reconstruction methods on numerical data through empirical evaluations and theoretical justifications.
Bio:
Dr. Xintao Wu is an Associate Professor of Software and Information Systems Department at University of North Carolina at Charlotte. He got his Ph.D. in Information Technology from George Mason University in August 2001, an ME degree in Computer Engineering from the Chinese Academy of Space Technology in 1997, and an BS degree in Information Science from the University of Science and Technology of China in 1994. His major research interests include data mining, data privacy and security, and social network analysis.
Dr. Wu is an editor of Springer's Journal of Intelligent Information Systems and Spanish Higher Research Council's Transaction on Data Privacy, and serves on program committees of many international conferences, including KDD, ICDM, SDM, PKDD, and PAKDD. He is serving as the program co-chair of the 2nd International Symposium on Data, Privacy and E-Commerce (ISDPE'10).
Dr. Wu is a recipient of NSF CAREER Award.