Network data is often incomplete. How can you get additional information and obtain more valuable information about a network? Tina Eliassi-Rad of Northeastern University will explain at a School of Computing, Informatics, and Decision Systems Engineering invited talk hosted by Hanghang Tong.
Learning to Expand Partially Observed Networks
Presented by Tina Eliassi-Rad, associate professor, College of Computer and Information Science, Northeastern University
Monday, January 22, 2018
Brickyard (BYENG) 210, Tempe campus [map]
No matter how meticulously constructed, network datasets are often partially observed and incomplete. For example, most of the publicly available data from online social networking services (such as Facebook and Twitter) are collected via apps, users who make their accounts public, and/or the resources available to the researcher or practitioner. Such incompleteness can lead to inaccurate findings.
Tina Eliassi-Rad will discuss the following scenario: Suppose that one has observed a network phenomenon via some form of sampling and has a budget to expand the incomplete network by asking for additional information about specific nodes, with the ultimate goal of obtaining the most valuable information about the network as a whole. The most valuable information depends on the task at hand. For instance, in epidemiological applications, adding hard-to-reach people to social networks is valuable. In other applications, expanding the boundary of the network is valuable.
The research question is: which node in the partially observed network should be further explored? This problem is related to active learning and respondent-driven sampling. Eliassi-Rad will present promising results using multi-armed bandits and reinforcement learning.
About the speaker
Tina Eliassi-Rad is an associate professor of computer science at Northeastern University in Boston, Massachusetts. She is also on the faculty of Northeastern’s Network Science Institute.
Prior to joining Northeastern, Eliassi-Rad was an associate professor of computer science at Rutgers University, and before that she was a member of technical staff and principal investigator at Lawrence Livermore National Laboratory.
Eliassi-Rad earned her doctorate in computer sciences (with a minor in mathematical statistics) at the University of Wisconsin-Madison. Her research is rooted in data mining and machine learning, and spans theory, algorithms and applications of massive data from networked representations of physical and social phenomena.
Eliassi-Rad’s work has been applied to personalized search on the web, statistical simulation data, fraud detection, mobile ad targeting and cyber situational awareness. Her algorithms have been incorporated into systems used by the government and industry (e.g., IBM System G Graph Analytics) as well as open source software (E.G., Stanford Network Analysis Project). In 2010, she received an Oustanding Mentor Award from the Office of Science at the U.S. Department of Energy.