Project Grant 2246067

Award Date 8/1/23
Completion Date 7/31/25
Dollars Obligated $175K
Federal Grant Program
47.070
Assistance Type
Project Grant
Place of Performance
Fountain Hill, PA 18015, USA
Similar Awards
This National Science Foundation project grant of $599,999 will fund research at Duke University from October 2022 through September 2026 towards developing secure methods for federated learning. Federated learning is an emerging machine learning technique that allows analysis of private data without centralized collection, but current methods lack security protections. Under the Computer and Information Science and Engineering program (CFDA 47.070), the researchers will explore new security...
This $348,573 project grant from the National Science Foundation's Division of Electrical, Communications and Cyber Systems, under the Engineering federal grant program (CFDA 47.041), will fund research at North Carolina State University from September 2022 through August 2025. The university will advance the frontiers of federated learning through exploring tradeoffs among learning performance, communication efficiency, privacy protection, and system robustness under a generalized...
The National Science Foundation Division of Information and Intelligent Systems awarded Duke University a $150,000 Project Grant under the Computer and Information Science and Engineering program (CFDA 47.070) for the period of September 1, 2021 through August 31, 2023. The grant funds the "EAGER: Distributed Heterogeneous Data Analytics via Federated Learning" project. This project supports the development of federated learning techniques to enable distributed and privacy-preserving...
This four-year $300,000 Project Grant from the National Science Foundation's Computer and Information Science and Engineering program aims to develop secure foundations for federated learning. Federated learning enables machine learning models to be collaboratively trained using data from many client devices without sharing private information. The researchers will investigate security vulnerabilities in federated learning's training phase, such as poisoning and backdoor attacks. They will...
The National Science Foundation awarded a $250,000 Project Grant to Lehigh University under the Computer and Information Science and Engineering federal grant program (CFDA 47.070) to support collaborative research titled "A UNIFIED FRAMEWORK FOR ANALYZING ADAPTIVE STOCHASTIC OPTIMIZATION METHODS BASED ON PROBABILISTIC ORACLES" from January 15, 2022 through December 31, 2024. The grant funding will support Lehigh University, along with any relevant sub-awardees, in conducting...
The National Science Foundation Division of Computing and Communication Foundations awarded Lehigh University $402,332 under the Computer and Information Science and Engineering federal grant program (CFDA 47.070) for the period of May 1, 2021 through April 30, 2024. The funding supports Lehigh University's REU SITE: INTELLIGENT AND SCALABLE SYSTEMS project located in Fountain Hill, Pennsylvania. The Computer and Information Science and Engineering program aims to support...
This $173,754 Project Grant awarded by the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) aims to develop an innovative privacy-preserving federated learning (FL) framework suitable for heterogeneous edge devices. The key objectives are to: 1) enable tailored device-specific models to mitigate biases and enhance performance across diverse computational capabilities and data distributions, 2) utilize differential privacy...
The National Science Foundation awarded a $300,000 project grant to Princeton University under the Computer and Information Science and Engineering program to support research towards securing federated learning. Over a four-year period ending September 2026, Princeton researchers will investigate security vulnerabilities in the training phase of federated learning models, develop provably secure federated learning methods to prevent poisoning and backdoor attacks, and create techniques to...
Lehigh University received a $185,424 Project Grant award from the National Science Foundation Directorate for Mathematical and Physical Sciences under the Mathematical and Physical Sciences federal grant program (CFDA 47.049). The award will support the development of a computational framework and software suite for high-fidelity simulation of multi-material flows involving multiple interacting fluids and structures. Key deliverables include an embedded boundary method capable of performing...
This Project Grant award from the National Science Foundation's (NSF) Mathematical and Physical Sciences Federal Grant Program (CFDA 47.049) aims to revolutionize the understanding and prediction of human mobility patterns. The $300,000 award to Lehigh University, to be executed from September 1, 2024 to August 31, 2027, will support the development of privacy-preserving, federated neural networks to analyze large-scale, cross-domain human mobility data from sources like smartphones, payment...

Lehigh University received a $175,000 Project Grant award from the National Science Foundation under the Computer and Information Science and Engineering federal grant program (CFDA 47.070) to conduct research towards improving the handling of heterogeneity and personalization in federated learning. The University will develop mathematical models and efficient algorithms to address issues in heterogeneous federated learning caused by data and device diversity. Researchers will design advanced personalized learning methods to balance global and personalized model performance. They will also study heterogeneous neural network aggregation, providing memory-efficient local training strategies for small devices and using knowledge distillation to improve local model generalization. The team proposes a unified federated learning framework integrating data-free knowledge aggregation and memory-efficient solutions to simultaneously address both heterogeneity challenges. The two-year project period began on August 1, 2023.

Generated 3/20/24, 8:54 AM