{"500631":{"#nid":"500631","#data":{"type":"event","title":"CSE Faculty Candidate Seminar - Alex Beutel: Beyond Who and What: Answering How and Why using Modeling Graphs","body":[{"value":"\u003Cp\u003E\u003Cstrong\u003EOverview:\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003ECan we model how fraudsters work to distinguish them from normal users? Can we predict not just which movie a person will like, but also why? How can we find when a student will become confused or where patients in a hospital system are getting infected? How can we effectively model large attributed graphs of complex interactions?\u0026nbsp;\u003C\/p\u003E\u003Cp\u003E\u0026nbsp;In this talk we will focus on understanding user behavior through modeling graphs.\u0026nbsp; Online, users interact not just with each other in social networks, but also with the world around them \u2013 supporting politicians, watching movies, buying clothing, searching for restaurants and finding doctors. These interactions often include insightful contextual information as attributes, such as the time of the interaction and ratings or reviews about the interaction.\u0026nbsp; The breadth of interactions and contextual information being stored presents a new frontier for graph modeling.\u0026nbsp; We demonstrate that by modeling \u003Cem\u003Ehow\u003C\/em\u003E fraudsters work, we can more effectively detect them, catching previously undetected fraud on Facebook, Twitter, Tencent Weibo and Flipkart.\u0026nbsp; We can predict \u003Cem\u003Ewhy\u003C\/em\u003E you will like a particular movie, giving an interpretable recommendation system that has state-of-the-art accuracy with a 4-times smaller model.\u0026nbsp; Last, we will discuss how to scale modeling of large hypergraphs, offering machine learning systems that scale to hundreds of gigabytes of data, billions of parameters and are up to 190-times faster than competitors.\u0026nbsp; We will conclude with my vision for the future of modeling graphs, covering exciting new applications, novel modeling approaches and upcoming challenges in scalable machine learning.\u003C\/p\u003E\u003Cp\u003E\u003Cstrong\u003EBio:\u003C\/strong\u003E\u003C\/p\u003E\u003Cp\u003EAlex Beutel is a Ph.D. candidate at Carnegie Mellon University\u0027s Computer Science Department. He previously received his B.S. from Duke University in computer science and physics. His primary interest is in modeling large graphs, with his Ph.D. thesis focused on large-scale user behavior modeling, covering recommendation systems, fraud detection, and scalable machine learning. His work has appeared in KDD, WWW, ICDM, SDM, AISTATS, and TKDD; and he has given tutorials on graph-based user behavior modeling at KDD, one of the premier data mining conferences, and CCS, one of the premier security conferences. He received the Best Paper Award at ACM GIS 2010, was a finalist for best paper in KDD 2014 and ASONAM 2012, and was awarded the Facebook Fellowship in 2013 and the NSF Graduate Research Fellowship in 2011.Beyond his research at CMU, Alex has worked on large-scale user behavior modeling at Facebook, Google, and Microsoft.\u003C\/p\u003E\u003Cp\u003EMore details can be found at \u003Ca href=\u0022http:\/\/alexbeutel.com\u0022 title=\u0022http:\/\/alexbeutel.com\u0022\u003Ehttp:\/\/alexbeutel.com\u003C\/a\u003E\u003C\/p\u003E","summary":null,"format":"limited_html"}],"field_subtitle":"","field_summary":[{"value":"\u003Cp\u003EIn this talk, Alex Beutel, Ph.D. candidate at Carnegie Mellon University\u2019s Computer Science Department will explain user behavior through modeling graphs.\u003C\/p\u003E","format":"limited_html"}],"field_summary_sentence":[{"value":"Faculty candidate presents information on using modeling graphs to understand users behavior."}],"uid":"28781","created_gmt":"2016-02-15 14:43:16","changed_gmt":"2017-04-13 21:16:37","author":"Anna Stroup","boilerplate_text":"","field_publication":"","field_article_url":"","field_event_time":{"event_time_start":"2016-02-26T09:00:00-05:00","event_time_end":"2016-02-26T10:00:00-05:00","event_time_end_last":"2016-02-26T10:00:00-05:00","gmt_time_start":"2016-02-26 14:00:00","gmt_time_end":"2016-02-26 15:00:00","gmt_time_end_last":"2016-02-26 15:00:00","rrule":null,"timezone":"America\/New_York"},"extras":[],"groups":[{"id":"50877","name":"School of Computational Science and Engineering"},{"id":"47223","name":"College of Computing"}],"categories":[],"keywords":[],"core_research_areas":[],"news_room_topics":[],"event_categories":[{"id":"1795","name":"Seminar\/Lecture\/Colloquium"}],"invited_audience":[{"id":"78751","name":"Undergraduate students"},{"id":"78761","name":"Faculty\/Staff"},{"id":"174045","name":"Graduate students"}],"affiliations":[],"classification":[],"areas_of_expertise":[],"news_and_recent_appearances":[],"phone":[],"contact":[{"value":"\u003Cp\u003EHost: Polo Chau, \u003Ca href=\u0022mailto:polo@gatech.edu\u0022\u003Epolo@gatech.edu\u003C\/a\u003E\u003C\/p\u003E","format":"limited_html"}],"email":[],"slides":[],"orientation":[],"userdata":""}}}