-
CS Colloquium Series Lecture: Greg ver Steeg (ISI): Detecting Influence in Social Networks
Thu, Apr 04, 2013 @ 03:30 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Greg ver Steeg, Information Sciences Institute (ISI)
Talk Title: Detecting Influence in Social Networks
Series: CS Colloquium
Abstract: Current tests for contagion in social network studies are flawed due to the confounding effects of latent homophily (i.e., ties form preferentially between individuals with similar hidden traits). We demonstrate a general method to lower bound the strength of causal effects in observational social network studies, even in the presence of arbitrary, unobserved individual traits. Our test requires no parametric assumptions and is based on connections with algebraic geometry and Bell inequalities in quantum physics. We demonstrate the effectiveness of our approach by correctly deducing the causal effects for examples previously shown to expose defects in existing methodology. Finally, we discuss preliminary results on data taken from the Framingham Heart Study showing that the spread of obesity cannot be explained by latent homophily.
I will also give a brief summary of other recent and ongoing research. One goal is to construct an information-theoretic foundation for unsupervised learning with preliminary success in discovering predictable relationships in social networks based only on content dynamics. Other topics include the statistical physics of networks and solving machine learning problems with quantum annealing.
Biography: Greg Ver Steeg is a computer scientist at USC's Information Sciences Institute. Ver Steeg received his PhD in physics from Caltech in 2009 for research in quantum information theory. His research has explored a diverse set of connections between computer science and physics dealing with machine learning, information theory, causal inference, and information processing. He is the recent winner of an AFOSR Young Investigator Award.
Host: CS Colloquium Series Lecture
Location: Seaver Science Library (SSL) - 150
Audiences: Everyone Is Invited
Contact: Assistant to CS chair