The National Science Foundation (NSF) awarded a $568,008 Project Grant under the CISE (Computer and Information Science and Engineering) Federal Grant Program (CFDA 47.070) to The Johns Hopkins University. This award, effective January 1, 2025 through December 31, 2027, will fund research and development of novel "non-canonical" graph representations, symmetries, and graph neural networks (GNNs) for applications in social networks, traffic networks, and molecular design. Key focus areas include designing scalable non-canonical graph representations, developing GNNs sensitive to large-scale graph structure, and exploiting graph symmetries in the spectral domain. The research activities aim to expand the computational capabilities of current GNN models and enable new applications in areas such as protein and macromolecule design. This project also includes diversity outreach and educational activities, such as mentoring Baltimore City public high school students and efforts to increase representation in applied mathematics and computer science.
Generated 3/4/25, 6:35 AM