[LAK'19] Keynote March 7 Keynote - Lise Getoor

Professor Lise Getoor (University of California Santa Cruz, USA) Scalable Collective Reasoning for Richly Structured Socio-Behavioral Data Learning analytics requires making sense of large, complex, and heterogeneous data. There are often data alignment and integration challenges. Data can be missing or noisy. Many times there is auxiliary domain knowledge, and often there is rich socio-behavioral data as well. In this talk, I will describe some common challenges for dealing with richly structured heterogeneous data. I will provide an introduction to probabilistic soft logic (PSL), an open-source toolkit being developed in my group that is well suited to the data integration, domain understanding, and performance analysis common in learning analytics. I will ground the presentation with several learning domain examples, including analysis of engagement and learning in online college and high-school MOOCs. Lise Getoor is a professor in the Computer Science Department and director of the Data, Discovery and Decisions Data Science Research Center at the University of California, Santa Cruz. Her research areas include machine learning, data integration and reasoning under uncertainty, with an emphasis on graph and network data. She has over 200 publications and extensive experience with machine learning and probabilistic modeling methods for graph and network data. She is a Fellow of the Association for Artificial Intelligence, has served as an elected board member of the International Machine Learning Society, the board of the Computing Research Association (CRA), and was co-chair for ICML 2011. She is the recipient of an NSF Career Award and twelve best paper and best student paper awards. She received her PhD from Stanford University in 2001, her MS from UC Berkeley, and her BS from UC Santa Barbara, and was a professor in the Computer Science Department at the University of Maryland, College Park from 2001-2013.