Project Grant 2403313
Award Date
10/1/24
Completion Date
9/30/27
Dollars Obligated
$300K
Federal Agency
Office of Advanced Cyberinfrastructure
Federal Grant Program
47.070
Assistance Type
Project Grant
Place of Performance
Charlottesville, VA, USA
Similar Awards
This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Program (CFDA 47.070) project grant awards $600,000 to the Rector & Visitors of the University of Virginia (University of Virginia) to develop innovative approaches for efficient training of Dynamic Graph Neural Network (DGNN) models on large-scale, time-varying graphs. The 3-year project, from October 2024 to September 2027, aims to create novel methods for graph partitioning, sampling, caching,...
The University of Virginia (UVA) received a $600,000 Project Grant from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) Program (CFDA 47.070) to advance federated graph machine learning (FGML) techniques. The project aims to 1) address data heterogeneity challenges in FGML, 2) develop novel algorithms to tackle label deficiency issues, and 3) strengthen data privacy protection for node attributes and graph structures. The research will produce...
This $299,574 federal Project Grant awarded by the National Science Foundation's Computer and Information Science and Engineering (CISE) program (CFDA 47.070) aims to develop a comprehensive cyberinfrastructure solution for training large-scale Graph Neural Networks (GNNs) to support spatiotemporal prediction and modeling of geographically distributed and heterogeneous data. The project led by Emory University will address key research challenges in formulating spatiotemporal prediction within a...
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) awarded a $250,000 Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) program to the University of Virginia. The grant supports the development of new physics-guided graph network models to capture complex, non-stationary, and poorly observed water dynamics in freshwater ecosystems. Key innovations include new graph-based architectures, continual learning strategies, and model initialization methods that leverage...
This $500,000 National Science Foundation project grant supports the development of new cyberattack detection approaches for large networks using complex graph modeling. Funded under the Computer and Information Science and Engineering program (CFDA 47.070), key products include constructing a complex graph model with graph refinement techniques to represent network traffic. The University of Virginia will design semi-supervised and weakly-supervised graph-based learning algorithms leveraging...
The National Science Foundation (NSF) awarded a $132,370 Project Grant under the Computer and Information Science and Engineering (CFDA 47.070) federal grant program to George Washington University. The grant, titled "Collaborative Research: Unlocking Complex Heterogeneity in Large Spatial-Temporal Data with Scalable Quantile Learning," aims to develop scalable and efficient quantile learning techniques to analyze large-scale, heterogeneous spatial-temporal data. The research seeks...
The National Science Foundation awarded a $499,979 project grant to the George Washington University under the Computer and Information Science and Engineering program (CFDA 47.070). The grant will support research towards developing high-performance machine learning techniques on graphs from October 1, 2021 to September 30, 2024. The Computer and Information Science and Engineering program aims to advance computing and informatics research and education. This award will further those goals by...
The National Science Foundation (NSF) awarded a $179,055 Project Grant to the University of Virginia under the Computer and Information Science and Engineering (CFDA 47.070) program. The grant supports collaborative research to develop privacy-preserving algorithms for fundamental problems in graph mining and network science. The project aims to create scalable, accurate graph differential privacy algorithms for applications like healthcare, social networks, finance, and computational...
This three-year, $532,241 Project Grant from the National Science Foundation's Division of Computer and Network Systems, under the Computer and Information Science and Engineering program (CFDA 47.070), will support the development of scalable algorithms, systems, and infrastructures for graph neural network training. The University of Massachusetts will develop a novel "split parallelism" training paradigm to transparently scale graph neural network training to large-scale graphs...