Namrata Banerji
PhD Student, Ohio State University
Talk recording
In this talk, I will present a reinforcement learning-based approach to task-focused network inference from time series attribute data of nodes. Rather than inferring static structures, our method discovers the temporally evolving network that optimally supports a given task—whether it's node classification, attribute prediction, or event forecasting. By learning the network topology that maximizes task performance, we move beyond conventional heuristics to a data-driven approach that adapts to complex, evolving systems. I will showcase applications and insights into how this framework can enhance predictive modeling in dynamic networks
About the speaker
Namrata Banerji is a fourth-year PhD student specializing in Dynamic Network Classification and Task-focused Inference. Her research focuses on using reinforcement learning to identify optimal network structures of entities (nodes) that enhance specific tasks, such as predicting node attributes. Collaborating with biologists studying primate behavior, her work is driven by an interest in group decision-making mechanisms in baboon societies. From August 2020 to June 2023, Namrata led the scripting and analysis team of The Ohio State University's COVID-19 monitoring initiative, contributing to effective policy decisions and the development of a nationally top-rated dashboard during the public health emergency.
Share this page:
