WNCG Seminar Series with Deepayan Chakrabarti

Friday, November 21, 2014
UTA 7.532

Personalized models often revolve around per-user parameters quantifying, say, an individual's interest in a certain product category or susceptibility to a certain type of advertisement, even after known features of the product and the person have been taken into account.  Social networks offer an appealing way to make inferences about such parameters, the intuition being that one's parameter is "close'' to that of one's friends.  We look at this basic scenario from two angles.

First, we consider a Bayesian model that incorporates the social network as a prior, and show that common methods of using the network via Gaussian fields are problematic, especially for real-world social networks with high median degrees. Second, we look at inferring user attributes from partially filled profiles user profiles in a social network, where the standard label propagation algorithm suffers from similar difficulties. In both cases, we find that a model that assumes "partial homophily'' works much better, yielding more accurate inferences and better theoretical guarantees.


Assistant Professor
University of Texas at Austin

Deepayan Chakrabarti is an Assistant Professor at the McCombs School of Business at the University of Texas at Austin. Prof. Chakrabarti focuses on Information, Risk and Operations Management. His research interests cover a broad range of problems in Machine Learning and Data Mining that focus particularly on mining large graphs and social networks, computational advertising, recommendation systems, web search and information retrieval. Prof. Chakrabarti received a B.Tech in Computer Science and Engineering from the Indian
Institute of Technology, and a M.S. and Ph.D. in Knowledge Discovering and Data Mining and Computational and Statistical Learning, respectively, from Carnegie Mellon University.