Learning Networks of People and Places from Location Data
Learning Networks of People and Places from Location Data
Thursday, November 12, 2009 | 1:00pm - 3:00pm
Location: 
Wiesner Room, 2nd Floor, MIT Media Lab
Speaker: 
Tony Jebara
Host/Chair: 
Deb Roy
Networks and graphs have become essential for understanding the online world, with applications ranging from the Web to Facebook. We will discuss building such networks in the offline real world by using mobile call and location data. By gathering long-term data from millions of mobile devices it becomes possible to track movement trends in real time in cities, learn networks of real places, and learn real social networks of people. We build graphs from this data using generalized matching algorithms and also apply novel visualization, clustering, and classification tools to them. For example, given a sparse graph between N high-dimensional data nodes, how do we faithfully view it in low dimension? We present an algorithm that improves dimensionality reduction by extending the Maximum Variance Unfolding method. But, given only a dataset of N samples or N people, how do we construct a graph in the first place? The space to explore is daunting, with 2^(N(N-1)/2) graphs to choose from, but we will show generalized matching algorithms that make the problem tractable. We discuss these algorithms and show applications to various networks and mobile phone data.
Biography: 
Tony Jebara is associate professor of computer science at Columbia University and co-founder of Sense Networks. He directs the Columbia Machine Learning Laboratory, whose research intersects computer science and statistics to develop new frameworks for learning from data with applications in vision, networks, spatio-temporal data, and text. Jebara has published over 70 peer-reviewed papers in conferences and journals including NIPS, ICML, UAI, COLT, JMLR, CVPR, ICCV, and AISTAT. He is the author of the book Machine Learning: Discriminative and Generative and co-inventor on multiple patents in vision, learning, and spatio-temporal modeling. In 2004, Jebara was the recipient of the Career award from the National Science Foundation. His work was recognized with a best paper award at the 26th International Conference on Machine Learning, a best student paper award at the 20th International Conference on Machine Learning, as well as an honorable mention from the Pattern Recognition Society in 2000. Jebara's research has been featured on television (ABC, BBC, New York One, TechTV) as well as in the popular press (The New York Times, Wired, BusinessWeek, IEEE Spectrum, and SlashDot). He obtained his PhD in 2002 from MIT. Recently, Esquire magazine named him one of their Best and Brightest of 2008. Jebara's lab is supported in part by the NSF, CIA, NSA, DHS, and ONR.