Classes & TalksThursday, December 10
ECE Seminar: Kevin Xu
Thursday, December 10 · 11 a.m.-12:30 p.m. · PHO 339
- When
- Thursday, December 10 · 11 a.m.-12:30 p.m.
- Where
- PHO 339
About this event
ECE Seminar: Kevin Xu
Title: Probabilistic Generative Models for Continuous-Time Dynamic Networks
Abstract: Networks are ubiquitous in science, serving as a natural representation for many complex physical, biological, and social systems. Probabilistic generative models for networks provide plausible mechanisms by which network data are generated in order to reveal insights into the underlying system. Complex systems are often time-varying, which has led to the development of dynamic network representations to enable modeling, analysis, and prediction of temporal dynamics.
In this talk, I introduce several probabilistic generative models for continuous-time dynamic networks that augment latent variable models for network structure with Hawkes processes to model temporal dynamics. I also introduce a semi-mechanistic model for temporal hypergraphs that models the creation of new hyperedges, edges that can involve more than two nodes, as noisy copies of previous hyperedges. Beyond typical prediction tasks, these models can be used for credit attribution, or simply attribution, where the objective is to quantify the influence or contribution of a prior edge to a future one. I demonstrate how these models can be used for analysis, prediction, and attribution on several real network data sets, including a network of militarized disputes between countries over time.
Bio: Kevin S. Xu received the B.A.Sc. degree from the University of Waterloo in 2007 and the M.S.E. and Ph.D. degrees from the University of Michigan in 2009 and 2012, respectively. He is a recipient of the NSF CAREER award, and his research has been supported by grants from the NSF, NIH, and American Heart Association. He is currently an assistant professor in the Department of Computer and Data Sciences at Case Western Reserve University. He was previously an assistant professor at the University of Toledo and held industry research positions at Technicolor and 3M. His main research interests are in probabilistic machine learning and network science with applications to health care, human dynamics, education, and wearable computing.
Listed by BU Today Featured Events (Localist), gathered by the Boston events calendar.