A1184
Title: A technique for consistent response prediction on a collection of time series of graphs
Authors: Aranyak Acharyya - Johns Hopkins University (United States) [presenting]
Francesco Sanna Passino - Imperial College London (United Kingdom)
Michael Trosset - Indiana University Bloomington (United States)
Carey Priebe - Johns Hopkins University (United States)
Abstract: The aim is to propose a novel methodology for the response prediction task on a collection of time series of networks. The setting involves a collection of time series of networks, some of them labeled with responses, while most are unlabeled. Exploiting an underlying low-dimensional structure, the method predicts the response consistently at an unlabeled time series of interest. The applicability of the method is demonstrated on real data for studying biological circuits governing learning capability in larval Drosophila.
