The National Science Foundation (NSF) awarded a $600,000 Project Grant under its Computer and Information Science and Engineering (CFDA 47.070) program to the Massachusetts Institute of Technology (MIT) with a project duration from March 1, 2025 to February 29, 2028.
The grant's objective is to develop a mathematical foundation to guide the principled use of graph data in a wide variety of machine learning tasks. The research aims to characterize how the geometry of the underlying latent space affects graph structure, study optimal algorithms for recovering latent feature vectors from observed graphs, and investigate computationally efficient semi-supervised learning algorithms leveraging graph data. This foundational research has the potential for downstream impact across applied domains such as improved drug discovery through more accurate predictions. The project involves mentoring PhD students and undergraduates, and integrating the research results into advanced academic courses.
Generated 3/18/25, 4:55 AM