Network Science Institute: Feedback driven graph learning
Title: Feedback driven graph learningSpeaker: Dr. Rajmonda Caceres, MIT Lincoln LabsLocation: 11th Floor, 177 Huntington Avenue, Boston, MA 02115, United StatesAbstractIn this talk, I will focus on the problem of constructing useful graph representations from noisy, multi-modal and temporal measurements. I will take the perspective that the downstream task should inform and guide the learning process and present two feedback-driven learning algorithms. I will discuss results and insights on various downstream tasks on both synthetic and real datasets. I will show that local topological metrics are often sufficient to guide the learning process towards better graph representations and that the quality of the graph does not transfer from one downstream task to the other. This is joint work with Jeremy Kun and Benjamin Fish.About the SpeakerDr. Rajmonda Caceres is a senior technical staff at MIT Lincoln Laboratory, in the Informatics and Decision Support Group. Her primary research interests are in the areas of network science, computational biology and data mining. She earned her PhD degree in mathematics and computer science from the University of Illinois at Chicago in 2012. Her current work focuses on methods for learning robust representations of complex networks, as well as learning in resource-constrained environments.
Monday, October 29, 2018 at 1:00pm