Project Grant 2318894
Award Date
8/1/23
Completion Date
7/31/26
Dollars Obligated
$300K
Federal Agency
Division of Mathematical Sciences
Federal Grant Program
47.049
Assistance Type
Project Grant
Place of Performance
Somerville, MA 02144, USA
Similar Awards
This Project Grant award from the National Science Foundation's (NSF) Division of Mathematical Sciences (CFDA 47.049 - Mathematical and Physical Sciences) supports research to develop novel mathematical models and efficient algorithms for deep learning on large-scale graph-structured data. The $249,999 award, spanning September 2024 to August 2027, aims to produce innovations in areas like graph convolutional networks, graph matching, and graph clustering. The research will involve graduate...
This five-year, $147,447 project grant from the National Science Foundation's Mathematical and Physical Sciences program aims to develop theoretical and computational tools for graph-based analysis of high-dimensional data. The grantee, Duke University, will conduct research in four integrated topics: learning graph diffusion with theoretical guarantees, robust graph affinity for data analysis, graph-based learning of intrinsic optimal transport, and generative modeling of graph data via...
This $300,000 Project Grant from the National Science Foundation Division of Mathematical Sciences under the Mathematical and Physical Sciences program (CFDA 47.049) will fund research into spectral methods for single and multiple graph inference networks. The grantee, North Carolina State University, will develop efficient parameter estimation methods for latent position graphs and valid two-sample testing procedures for comparing latent position graphs while ignoring irrelevant features. The...
This $600,000 Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) supports research to develop a mathematical foundation for using graph data in machine learning. The key goals are to: 1) characterize how the geometry of the underlying latent space affects graph structure, 2) devise optimal algorithms for recovering latent feature vectors from observed graphs, and 3) find computationally efficient...
This $229,461 Project Grant award from the National Science Foundation's Mathematical and Physical Sciences program (CFDA 47.049) supports the development and analysis of novel self-supervised probabilistic graph structure learning models. The goal is to uncover latent representations hidden within large datasets, which can provide valuable insights across diverse applications like cancer research and environmental analysis. The research will involve creating advanced mathematical models,...
The National Science Foundation (NSF) has awarded a $300,000 Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) program to the Old Dominion University Research Foundation (Odurf) to develop a new holistic and standardized graph learning framework for open-world and streaming network learning. Key objectives include characterizing complex and evolving graph data representations, identifying the emergence of new classes, and generalizing graph models across...
The National Science Foundation (NSF) Division of Mathematical Sciences awarded a $125,000 Project Grant to the University of Utah for the project "COLLABORATIVE RESEARCH: ATD: FAST ALGORITHMS AND NOVEL CONTINUOUS-DEPTH GRAPH NEURAL NETWORKS FOR THREAT DETECTION" under the Mathematical and Physical Sciences program (CFDA 47.049). The project aims to advance graph neural network (GNN) algorithms for improved accuracy and efficiency in threat detection within multivariate time series...
This $100,000 Project Grant awarded by the National Science Foundation (NSF) Division of Mathematical Sciences under the Mathematical and Physical Sciences program (CFDA 47.049) supports a research project by the University of California, Los Angeles (UCLA) to develop active learning algorithms for detecting patterns of activity in complex, multimodal data structures organized as multiplex networks. The project aims to address the challenge of extracting insights from large, heterogeneous...
The National Science Foundation (NSF) Division of Mathematical Sciences awarded a $249,999 Project Grant to Trustees of Boston University to develop an innovative approach to change-point and anomaly detection using satellite data. The research aims to address challenges in tracking deforestation, degradation, and forest regrowth by leveraging new mathematical frameworks and artificial intelligence techniques. The project will explore applications in areas such as human migration, climate...
This National Science Foundation (NSF) Mathematical and Physical Sciences (CFDA 47.049) grant awarded to The Trustees of Princeton University (Princeton) totals $120,000 over the project period of June 1, 2024 to May 31, 2027. The grant supports Princeton's research on the structural properties and algorithmic complexity of families of graphs, with a focus on using tree decompositions and forbidden induced subgraphs to better understand and solve challenging graph theory problems. The research...